© 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. 38245
    Prev
    Next
    INDEX
    Explanations

    symbols and titles

    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
    ökning
    -1.10
     within
    -1.01
     trimestre
    -0.98
     السياس
    -0.96
     intérprete
    -0.94
     аллер
    -0.92
    tyfik
    -0.92
    </tfoot>
    -0.91
     interesan
    -0.91
     Armee
    -0.91
    POSITIVE LOGITS
     EIGHT
    1.05
     khoe
    1.03
     appartenant
    0.99
     RANDOM
    0.99
     MONTHLY
    0.98
     poème
    0.98
     iluminación
    0.97
    '
    0.96
    èdent
    0.95
    を変
    0.95
    Activations Density 0.000%

    No Known Activations