© 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. 22-GEMMASCOPE-RES-131K
    7. 127707
    Prev
    Next
    INDEX
    Explanations

    year, abbreviation, or code

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     by
    -1.04
     it
    -1.02
     also
    -0.93
    fam
    -0.88
    []
    -0.85
    <h3>
    -0.84
     if
    -0.82
    Also
    -0.82
    ankar
    -0.81
     еле
    -0.81
    POSITIVE LOGITS
    Forrás
    1.05
    Mitglieder
    1.03
    鎳
    1.02
    Mål
    1.00
    hassee
    1.00
    なりません
    0.97
     Flä
    0.96
     navegador
    0.95
    vinilo
    0.94
     střed
    0.94
    Activations Density 0.000%

    No Known Activations