© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13693
    Prev
    Next
    INDEX
    Explanations

    internal, local, domestic

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

    The neuron strongly activates on words and phrases describing scientific or investigative research contexts (e.g. investigating, studies, laboratory, turned his lens on).

    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_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
    ierzchn
    0.48
    enov
    0.48
    jgl
    0.47
    解放
    0.46
    ъл
    0.45
     pubblica
    0.45
    츨
    0.45
    õe
    0.45
    MQTT
    0.44
    imidazo
    0.44
    POSITIVE LOGITS
     domestically
    2.52
     local
    2.47
     locally
    2.47
    本地
    2.42
    local
    2.41
     domestic
    2.38
     lokal
    2.36
     स्थानीय
    2.31
    locally
    2.27
     LOCAL
    2.23
    Activations Density 0.810%

    No Known Activations