© 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. 72020
    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
    趼
    -1.05
    ⅘
    -1.04
    ٴ
    -1.02
    juego
    -1.01
    Série
    -1.01
    Komentar
    -1.00
     Ayrıca
    -1.00
    Книга
    -0.97
    ⒈
    -0.97
     삼
    -0.96
    POSITIVE LOGITS
    and
    1.18
    \"
    1.03
     ’
    1.02
    一只
    1.00
    !!!!!!
    0.99
    ---
    0.98
     il
    0.98
     \"
    0.97
     conver
    0.97
    root
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.