© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46746
    Prev
    Next
    INDEX
    Explanations

    violation of safety guidelines

    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_31_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
    inprogress
    0.53
    u
    0.52
    ח
    0.50
    াহিনী
    0.49
    მი
    0.48
     ע
    0.48
     retrou
    0.48
    hidrat
    0.48
    되었다
    0.47
     නිර්
    0.47
    POSITIVE LOGITS
     violations
    0.68
     violate
    0.65
     violated
    0.62
     violation
    0.60
     нарушения
    0.59
     violates
    0.58
    '
    0.56
    违反
    0.55
     нарушение
    0.54
    违
    0.54
    Activations Density 0.061%

    No Known Activations