© 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. 129295
    Prev
    Next
    INDEX
    Explanations

    file names or table names

    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
    RTLD
    -0.91
     Bâ
    -0.90
     gik
    -0.88
    Restaurants
    -0.85
     角色
    -0.85
     montes
    -0.84
     trän
    -0.84
    XXIII
    -0.84
     както
    -0.84
    cliffe
    -0.84
    POSITIVE LOGITS
     obligación
    0.95
     partenaires
    0.94
     rappresenta
    0.93
    having
    0.92
    其他
    0.92
     other
    0.92
     другой
    0.92
    两者
    0.92
     its
    0.90
    causing
    0.90
    Activations Density 0.045%

    No Known Activations