© 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. 24-GEMMASCOPE-2-RES-16K
    4. 5104
    Prev
    Next
    INDEX
    Explanations

    [Project Name] or [Colleague's Name]

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on colons (:) that introduce lists, tables, or section‐style entries.

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

    phrases describing services or categories offered by businesses in directory listings.

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

    phrases that introduce a formal list of offerings or service categories in business/organization listings.

    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_24_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
    জ্জনক
    1.02
     seguramente
    0.96
     aggiunto
    0.94
    cstdlib
    0.93
     direita
    0.91
    𝒂
    0.88
     Aéroport
    0.88
     adequado
    0.88
     quente
    0.86
     kajian
    0.86
    POSITIVE LOGITS
     consultation
    0.70
    ना
    0.64
     પછી
    0.63
    ம்
    0.61
    on
    0.59
    یه
    0.59
    ofthe
    0.57
    ervice
    0.57
    上的
    0.57
    هل
    0.56
    Activations Density 0.000%

    No Known Activations