© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4071
    Prev
    Next
    INDEX
    Explanations

    patterns and descriptions

    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_40_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
    蛩
    0.35
    謖
    0.35
     :-)
    0.34
     '.',
    0.33
     ودي
    0.33
     অনুয
    0.32
    㿝
    0.32
    راتيج
    0.32
    耒
    0.32
    ပါသည်။
    0.31
    POSITIVE LOGITS
    <h2>
    0.42
    *
    0.39
    Check
    0.36
    <h3>
    0.35
    nc
    0.32
     Level
    0.32
    All
    0.32
    What
    0.31
    check
    0.31
    auto
    0.30
    Activations Density 0.000%

    No Known Activations