© 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. 45554
    Prev
    Next
    INDEX
    Explanations

    To deliver

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

    refusal to harmful requests

    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
    ↵
    0.72
    ↵↵
    0.55
     V
    0.51
     H
    0.50
     ,
    0.48
     W
    0.48
    C
    0.47
    H
    0.47
     C
    0.46
    W
    0.46
    POSITIVE LOGITS
     presenceData
    0.51
     étapes
    0.48
    🕘
    0.48
    郯
    0.47
    녠
    0.47
    试点
    0.46
    멱
    0.46
     allError
    0.46
    哫
    0.46
    营养
    0.46
    Activations Density 0.000%

    No Known Activations