Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84979
    Prev
    Next
    INDEX
    Explanations

    harm to victims

    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
     linguaggio
    0.51
    кат
    0.50
     Erkrank
    0.47
     DISABLE
    0.46
     überprüft
    0.46
    跏
    0.45
    ()<<"
    0.45
     sendMessage
    0.44
     Meteorology
    0.44
     getString
    0.44
    POSITIVE LOGITS
    ground
    0.49
    but
    0.46
    a
    0.46
    range
    0.46
    s
    0.45
    the
    0.44
    sel
    0.44
     अने
    0.44
    性の
    0.44
     ਸਾ
    0.44
    Activations Density 0.011%

    No Known Activations