© 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. 15663
    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
    Negative Logits
    section
    -0.98
    connect
    -0.91
    raise
    -0.91
    可以用
    -0.90
    tral
    -0.90
    х
    -0.90
     основании
    -0.89
    а
    -0.88
    uet
    -0.88
    ри
    -0.88
    POSITIVE LOGITS
     eneste
    1.12
    鬟
    0.98
     oficio
    0.98
     következő
    0.93
     næste
    0.93
    بسم
    0.92
    鵟
    0.92
    elebr
    0.92
     ТАК
    0.92
    snowy
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.