© 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. 16605
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     less
    -0.98
    xem
    -0.97
    acı
    -0.96
    lihatan
    -0.94
    mulher
    -0.93
     since
    -0.91
     ostensibly
    -0.90
     what
    -0.90
    Xem
    -0.89
    datable
    -0.89
    POSITIVE LOGITS
    <bos>
    1.30
    があり
    1.20
    で
    1.01
     sogar
    0.99
     incluso
    0.98
     faço
    0.98
    では
    0.96
    澁
    0.96
     jo
    0.92
    それも
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.