© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142048
    Prev
    Next
    INDEX
    Explanations

    football

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.88
    ي
    0.79
    كور
    0.77
    ка
    0.75
    क
    0.75
    i
    0.73
    ে
    0.72
    kelig
    0.71
    σει
    0.70
    κολ
    0.70
    POSITIVE LOGITS
    ing
    0.94
    _
    0.71
    PA
    0.70
    ী
    0.69
    ü
    0.68
    GI
    0.66
    WITH
    0.66
    рия
    0.65
    -
    0.65
    Ž
    0.65
    Activations Density 0.001%

    No Known Activations