© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6769
    Prev
    Next
    INDEX
    Explanations

    drunk driving and DUIs

    np_acts-logits-general · gemini-2.5-flash-lite

    alcohol and performance decline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    匱
    0.47
    ױ
    0.46
     поль
    0.44
    Polish
    0.41
    scm
    0.41
     इनोवेशन
    0.41
    偐
    0.40
    墳
    0.40
    semantic
    0.39
    BITMAP
    0.39
    POSITIVE LOGITS
     alcohol
    1.18
     Alcohol
    1.11
     drunk
    1.06
    alcohol
    1.03
     DUI
    1.03
    Alcohol
    1.02
     алкого
    1.02
     drunkenness
    0.99
     alcool
    0.97
     drunken
    0.97
    Activations Density 0.104%

    No Known Activations