© 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. 22-GEMMASCOPE-RES-131K
    7. 130128
    Prev
    Next
    INDEX
    Explanations

    links and downloads

    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
     ಸ
    -1.23
    These
    -1.06
     Any
    -0.99
    Any
    -0.98
     you
    -0.97
     your
    -0.95
    くんの
    -0.94
    tissimi
    -0.93
     During
    -0.93
    ↵↵↵↵↵↵↵↵↵↵
    -0.93
    POSITIVE LOGITS
    accessed
    1.05
    вање
    1.01
     accessed
    1.01
    vailable
    0.99
     ibland
    0.96
     šaty
    0.94
     vinaigre
    0.94
     dostępne
    0.93
     JOSÉ
    0.93
    влено
    0.92
    Activations Density 0.002%

    No Known Activations