© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5856
    Prev
    Next
    INDEX
    Explanations

    highly subjective

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

    The neuron is triggered by structured directory/listing language—especially business listing headers and service‐offering phrases like “is offered:” and similar category descriptors.

    oai_token-act-pair · o4-miniTriggered 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
     dalej
    0.75
     séptimo
    0.70
    gün
    0.70
    س
    0.68
     Хабаров
    0.66
    ছাড়া
    0.66
    gleichen
    0.65
    팔
    0.65
    시간
    0.64
     스
    0.64
    POSITIVE LOGITS
     beverages
    0.89
     of
    0.88
     should
    0.84
     drugs
    0.76
    許多
    0.75
     imports
    0.73
     fhould
    0.71
     and
    0.70
     abused
    0.70
     shipments
    0.70
    Activations Density 0.002%

    No Known Activations