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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 34132
    Prev
    Next
    INDEX
    Explanations

    driven mad

    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_53_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
     broadly
    0.35
    投注
    0.35
    /\
    0.34
    /<%=
    0.34
     perme
    0.33
     biais
    0.33
     headed
    0.33
    概
    0.33
    するための
    0.33
     satisfying
    0.33
    POSITIVE LOGITS
     mad
    0.82
     crazy
    0.70
     wild
    0.67
    mad
    0.66
    crazy
    0.66
     nuts
    0.61
     insane
    0.61
     desperate
    0.57
    Mad
    0.57
    wild
    0.56
    Activations Density 0.004%

    No Known Activations