© 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. 11356
    Prev
    Next
    INDEX
    Explanations

    specific group names or entities

    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
     a
    -1.12
     Gehäuse
    -0.97
     using
    -0.96
    外界
    -0.96
     giudizio
    -0.95
     battling
    -0.91
    ํา
    -0.90
     external
    -0.90
     fighting
    -0.88
     from
    -0.88
    POSITIVE LOGITS
     lubricating
    1.05
    াদের
    0.98
     Bagaimana
    0.95
     esca
    0.93
    חים
    0.93
    bling
    0.92
    geordnete
    0.91
    ección
    0.90
    人数
    0.89
    informationen
    0.89
    Activations Density 0.154%

    No Known Activations