© 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. 114236
    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
     bestellen
    -0.95
    ꦠ
    -0.95
     wrze
    -0.93
    中午
    -0.91
     российского
    -0.91
     wies
    -0.91
     thuy
    -0.91
    で大
    -0.90
     their
    -0.89
    sino
    -0.88
    POSITIVE LOGITS
    Amsterdam
    1.00
     BufferedWriter
    0.99
     PrintWriter
    0.96
     quirk
    0.94
    我們
    0.93
     Milán
    0.93
    เรา
    0.91
    Eyes
    0.90
    чной
    0.90
    acka
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.