© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49733
    Prev
    Next
    INDEX
    Explanations

    documentation summary comment

    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_34/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
     but
    -0.91
    饗
    -0.90
    ……」
    -0.90
     even
    -0.89
     almost
    -0.85
     sintomas
    -0.84
    CONTENIDO
    -0.84
    伯爵
    -0.84
    しましたが
    -0.83
     TAMB
    -0.83
    POSITIVE LOGITS
    Summary
    1.21
    summary
    1.20
     <
    1.05
     summary
    1.05
    T
    0.95
    ™
    0.95
    RS
    0.95
    begin
    0.94
     daß
    0.93
    YS
    0.91
    Activations Density 0.003%

    No Known Activations