© 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. 6792
    Prev
    Next
    INDEX
    Explanations

    specific named questionnaires

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

    The neuron detects occurrences of the word “questionnaire” (i.e. mentions of a questionnaire or survey instrument).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    
    -3.80
    樒
    -3.56
    埽
    -3.36
    𖣘
    -3.23
    鯪
    -3.08
    寕
    -3.00
    佧
    -3.00
     diminta
    -2.83
    ㍑
    -2.78
     mengucap
    -2.72
    POSITIVE LOGITS
    ↵
    3.13
     but
    2.91
    ?
    2.50
    .
    2.50
    と言って
    2.42
    齷
    2.31
    ;
    2.28
     to
    2.27
    狆
    2.25
     cliquer
    2.20
    Activations Density 0.008%

    No Known Activations