© 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. 64338
    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
     nombreuses
    -1.10
     przyczyn
    -1.00
    то
    -0.97
    多く
    -0.96
    하다
    -0.94
    损坏
    -0.94
    ième
    -0.93
    それを
    -0.93
     possu
    -0.90
    داشت
    -0.88
    POSITIVE LOGITS
    窺
    1.11
    鏖
    1.09
     with
    1.09
     насеља
    1.04
     instead
    0.99
    ୀ
    0.97
    schuhe
    0.96
    凰
    0.96
    zt
    0.94
     также
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.