© 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. 32881
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     still
    -1.10
    ческому
    -0.90
    ódnica
    -0.90
    だが
    -0.90
     Pfund
    -0.90
    もう
    -0.88
     Brunnen
    -0.88
    still
    -0.85
    ？」
    -0.81
     🙄
    -0.81
    POSITIVE LOGITS
     også
    1.30
    ampingi
    1.05
     yakın
    0.99
    Vikt
    0.99
    きち
    0.96
     stär
    0.95
    となりました
    0.94
     protezione
    0.94
     gefüllt
    0.92
     также
    0.91
    Activations Density 0.005%

    No Known Activations