© 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. 32966
    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
    Not in Any Lists

    No Comments

    Negative Logits
     more
    -1.15
     when
    -1.12
     their
    -1.12
    kesan
    -1.09
    不少
    -1.09
    無し
    -1.09
     overras
    -1.07
    Ď
    -1.05
     abgerufen
    -1.04
     maž
    -1.00
    POSITIVE LOGITS
     thậm
    1.03
     এই
    1.03
    澁
    1.01
    かで
    0.99
    特别是
    0.99
     crests
    0.97
    Inclu
    0.96
    g
    0.95
    遊ぶ
    0.94
    Inaug
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.