© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26252
    Prev
    Next
    INDEX
    Explanations

    language or code syntax

    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
    燴
    -1.03
    Title
    -0.99
    費
    -0.91
    Soul
    -0.88
    FFECT
    -0.87
    trong
    -0.86
    م
    -0.85
    Dual
    -0.83
    Ry
    -0.82
    பி
    -0.82
    POSITIVE LOGITS
    مشخص
    1.00
     söyledi
    0.98
    ونج
    0.96
     giallo
    0.95
    &
    0.94
     with
    0.93
     Réponses
    0.93
     Quels
    0.92
     kyt
    0.90
     Véri
    0.89
    Activations Density 0.000%

    No Known Activations