© 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. 15098
    Prev
    Next
    INDEX
    Explanations

    limiting results count

    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
     Ajoutez
    -1.10
    يئة
    -1.09
     такие
    -1.00
     funkcji
    -0.99
     tetrachloride
    -0.98
     主题
    -0.98
    上げます
    -0.96
     hän
    -0.94
     inapropiados
    -0.93
     poitrine
    -0.93
    POSITIVE LOGITS
     limit
    1.00
     weeks
    0.98
     limita
    0.96
    limit
    0.96
     LIMIT
    0.94
    uminense
    0.94
     nombrado
    0.88
    umab
    0.88
     Limit
    0.86
    alisco
    0.86
    Activations Density 0.006%

    No Known Activations