© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 389
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on sequences of items—especially commas, colons, “and,” and other list markers—i.e. enumerations or bullet-list style presentations of features or benefits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    detailed descriptions of programs, services, or offerings, particularly in organizational or institutional contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions and enumerations of organized programs and services (grants, trainings, tours, community support initiatives) and how they serve beneficiaries, including features, activities, and logistics.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الناس
    0.47
     ludzi
    0.47
    🌫
    0.46
     civilisation
    0.45
     monstru
    0.44
    Temperatura
    0.43
     राजवंश
    0.43
    🗡
    0.43
     mankind
    0.43
     kẻ
    0.42
    POSITIVE LOGITS
     workshops
    1.02
     mentoring
    1.02
     mentorship
    0.98
     counseling
    0.96
     seminars
    0.94
     outreach
    0.91
     webinars
    0.91
     internships
    0.91
     scholarships
    0.90
     trainings
    0.89
    Activations Density 7.407%

    No Known Activations