© 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. 24970
    Prev
    Next
    INDEX
    Explanations

    mathematical sciences

    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
     any
    -1.16
     also
    -0.97
     anything
    -0.95
     überprüfen
    -0.95
    It
    -0.93
    Also
    -0.91
    But
    -0.90
     surrounding
    -0.88
    時間も
    -0.88
    any
    -0.87
    POSITIVE LOGITS
    номер
    1.21
    风景
    0.99
    tomorrow
    0.96
    ikä
    0.96
     Ө
    0.95
    nö
    0.94
    gunaan
    0.93
    おわりに
    0.93
     件
    0.92
    ВЕ
    0.92
    Activations Density 0.044%

    No Known Activations