© 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. 45463
    Prev
    Next
    INDEX
    Explanations

    payer status, haircut, paycheck

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    愎
    -2.97
     Eigentü
    -2.64
     člov
    -2.58
    窳
    -2.56
    麁
    -2.55
     jornadas
    -2.52
    ឵
    -2.45
     essayé
    -2.44
     verdades
    -2.42
    ｱ
    -2.41
    POSITIVE LOGITS
    ing
    3.81
    럿
    2.61
    to
    2.58
    鈇
    2.38
    Of
    2.36
    捽
    2.34
     untuk
    2.28
    坶
    2.25
    ཋ
    2.19
    耵
    2.19
    Activations Density 0.009%

    No Known Activations