© 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. 83929
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Награ
    -1.10
    cores
    -0.99
     masih
    -0.98
    Alte
    -0.97
     ***!
    -0.96
     novidades
    -0.96
    好在
    -0.96
    پرو
    -0.94
     bomberos
    -0.93
     penghargaan
    -0.92
    POSITIVE LOGITS
    |
    0.97
     also
    0.93
    poque
    0.92
     who
    0.89
     until
    0.87
     ویکی‌پدیا
    0.87
    零
    0.85
    昵
    0.85
     Nếu
    0.85
    ское
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.