© 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. 64600
    Prev
    Next
    INDEX
    Explanations

    class inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ixote
    -1.07
     weißem
    -1.02
     geloof
    -1.01
     ponieważ
    -1.00
    気がする
    -0.99
     potrebné
    -0.96
    を変える
    -0.95
     AÑO
    -0.95
    ungkinkan
    -0.95
    だけです
    -0.94
    POSITIVE LOGITS
     充電
    1.04
    鏘
    1.04
    ıkları
    1.04
     prêtres
    1.03
     zis
    1.03
     turist
    1.02
    ㅊ
    1.01
     Rakyat
    0.98
    🥘
    0.98
    Stéphane
    0.97
    Activations Density 0.026%

    No Known Activations