© 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. 83678
    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
    enské
    -1.06
     DONT
    -1.03
     korean
    -1.01
    PKG
    -1.00
     geda
    -0.99
    槁
    -0.97
    ᠢ
    -0.97
    ueel
    -0.97
    Cuad
    -0.97
    ErrUnexpectedEOF
    -0.96
    POSITIVE LOGITS
     как
    1.02
    yx
    0.97
     bilden
    0.94
     their
    0.94
     apparently
    0.93
     same
    0.92
     public
    0.91
     even
    0.90
     seem
    0.90
     either
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.