© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11569
    Prev
    Next
    INDEX
    Explanations

    separators and connectors

    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
     cend
    -0.77
     SUPPLEMENT
    -0.77
     harvested
    -0.77
    你
    -0.76
     アウト
    -0.76
     与
    -0.75
    getDeclared
    -0.74
    Corporate
    -0.73
    menden
    -0.73
    要
    -0.73
    POSITIVE LOGITS
     schlug
    0.87
     requerimientos
    0.82
     záz
    0.81
     zmian
    0.81
     barev
    0.80
    causing
    0.80
    Leírás
    0.80
     zaji
    0.80
     fatiga
    0.79
    mca
    0.79
    Activations Density 0.046%

    No Known Activations