© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    violent scenarios involving men and women

    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
     युवाओं
    0.47
    來
    0.42
     बढ़ावा
    0.39
    তাসীন
    0.38
     సమావేశ
    0.38
     justement
    0.38
    ್ರೀ
    0.38
    闲
    0.38
    饭
    0.37
     semin
    0.36
    POSITIVE LOGITS
     stabbed
    0.59
     died
    0.57
     قتل
    0.52
    قتل
    0.50
     murder
    0.50
     killed
    0.49
     abducted
    0.49
     suspected
    0.49
     поги
    0.48
     theft
    0.48
    Activations Density 0.020%

    No Known Activations