© 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. 4537
    Prev
    Next
    INDEX
    Explanations

    Java library imports

    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
     gill
    0.42
    潵
    0.40
    蛏
    0.40
    疥
    0.39
     Cessna
    0.38
    赊
    0.38
     meringue
    0.38
     क्रॉप
    0.37
     アイアン
    0.37
    莴
    0.37
    POSITIVE LOGITS
    util
    0.60
    security
    0.45
    QtCore
    0.43
    event
    0.43
    math
    0.43
    contrib
    0.43
    routing
    0.42
    utils
    0.42
     util
    0.42
    core
    0.42
    Activations Density 0.015%

    No Known Activations