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

    Neuronpedia

    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. 84421
    Prev
    Next
    INDEX
    Explanations

    escaping from situations

    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
    е
    0.79
    '
    0.67
    ,”
    0.62
    iyê
    0.62
    บริหาร
    0.57
    é
    0.55
    をや
    0.54
    ત
    0.53
    лер
    0.53
    ”,
    0.52
    POSITIVE LOGITS
     escape
    1.27
     escapes
    1.13
    escape
    1.09
     escaped
    1.08
     Escape
    1.08
     escaping
    1.07
    Escape
    1.06
    逃
    0.97
    escaping
    0.91
    ESCAPE
    0.90
    Activations Density 0.013%

    No Known Activations