© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38627
    Prev
    Next
    INDEX
    Explanations

    avid supporter or advocate

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

    This neuron detects words expressing strong personal enthusiasm or support (e.g. “avid,” “enthusiastic,” “supporter”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     It
    -1.96
     their
    -1.84
     Makes
    -1.83
     some
    -1.77
     Some
    -1.66
    錚
    -1.60
     Sometimes
    -1.59
     because
    -1.57
     There
    -1.57
     there
    -1.54
    POSITIVE LOGITS
    蔸
    2.45
    \
    1.83
    鹇
    1.82
     ANSWERS
    1.66
     YOUTH
    1.60
     itali
    1.60
    '';
    1.59
     burbu
    1.55
     zoude
    1.55
     AUDIO
    1.54
    Activations Density 0.029%

    No Known Activations