© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 275
    Prev
    Next
    INDEX
    Explanations

    code constructs and URLs

    np_acts-logits-general · gemini-2.5-flash-lite

    programming keywords (reg, call, sort)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    啭
    0.34
     পরিশ
    0.31
    🏔
    0.30
     ჩატი
    0.29
     জমা
    0.28
    殡
    0.27
     इनो
    0.27
    疖
    0.27
     gắng
    0.27
     প্রয়োজনে
    0.27
    POSITIVE LOGITS
    8
    0.53
    9
    0.49
    7
    0.48
    6
    0.45
    5
    0.42
    4
    0.42
     (
    0.38
    3
    0.37
    -
    0.32
    （
    0.31
    Activations Density 0.015%

    No Known Activations