© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60245
    Prev
    Next
    INDEX
    Explanations

    bypass safety filters

    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_all/layer_41_width_262k_l0_big
    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
     تق
    0.43
     arxivləşdirilib
    0.39
    깎
    0.39
     bolsillo
    0.38
     distant
    0.38
    bundles
    0.37
    팬
    0.37
     चक
    0.37
     ಸಂಧಿ
    0.36
     कलेक्टर
    0.36
    POSITIVE LOGITS
     filling
    2.03
     fill
    1.91
    Filling
    1.86
     fills
    1.84
     Filling
    1.84
    Fill
    1.81
     Fill
    1.80
     запол
    1.75
    fill
    1.68
    filling
    1.68
    Activations Density 0.003%

    No Known Activations