© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12259
    Prev
    Next
    INDEX
    Explanations

    metadata and descriptions

    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
    ＊＊＊＊
    -0.92
     didel
    -0.91
    romas
    -0.89
    rethe
    -0.87
    长安
    -0.87
    性は
    -0.82
    ɸ
    -0.82
    waitUntil
    -0.82
     उन्ह
    -0.81
    🚧
    -0.81
    POSITIVE LOGITS
     location
    1.30
     type
    1.15
     method
    1.10
     genre
    1.05
     localización
    1.04
     description
    1.03
     dates
    1.02
     ocupación
    1.02
     Description
    1.02
     locations
    0.98
    Activations Density 0.112%

    No Known Activations