© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    regex character sets or code delimiters

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

    This neuron fires on numeric tokens—especially floating-point numbers (decimal values) used in citations or measurements.

    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
     involuntary
    0.52
     amyloid
    0.50
    沭
    0.50
    プレス
    0.48
     urgently
    0.48
    深入
    0.47
    gesterone
    0.47
     presc
    0.46
    ປະ
    0.46
     sweater
    0.46
    POSITIVE LOGITS
    Caption
    0.60
     работы
    0.59
    auk
    0.57
    ándole
    0.56
     पठान
    0.55
    ૯
    0.55
    哳
    0.55
     வசன
    0.55
     Treated
    0.54
     Barton
    0.54
    Activations Density 0.020%

    No Known Activations