© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5125
    Prev
    Next
    INDEX
    Explanations

    alcohol and drinking

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

    alcohol and drinking

    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_53_width_65k_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
     Hartree
    0.39
     ICT
    0.38
    孳
    0.38
    াড়া
    0.38
     Huawei
    0.38
    unpkg
    0.37
     ნაკ
    0.37
    綘
    0.37
    华为
    0.36
    Huawei
    0.36
    POSITIVE LOGITS
     alcohol
    3.14
    喝酒
    3.08
     booze
    2.98
    alcohol
    2.97
     alkohol
    2.97
     алкого
    2.97
    Alcohol
    2.95
     Alcohol
    2.94
     alcoholic
    2.92
     शराब
    2.84
    Activations Density 0.264%

    No Known Activations