© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    Council and directors

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

    This neuron detects mentions of formal “Council for…” or “Council of…” organization names.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     OSX
    0.58
     Idee
    0.57
    лет
    0.57
     policeman
    0.55
     Motiv
    0.55
    ietta
    0.55
    ண்ண
    0.54
     করিয়৷
    0.54
     Aś
    0.54
     অবকাশ
    0.53
    POSITIVE LOGITS
     councils
    0.78
    ys
    0.71
     ministers
    0.67
     advisors
    0.66
     मंत्रियों
    0.66
     pradesh
    0.66
     Councils
    0.64
    Europe
    0.63
     advisers
    0.63
    council
    0.63
    Activations Density 0.072%

    No Known Activations