© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1797
    Prev
    Next
    INDEX
    Explanations

    alcoholic beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    幼儿
    1.17
    ัศ
    1.16
    蚂
    1.12
    teacher
    1.10
     Tomlinson
    1.09
     द्विवेदी
    1.08
     کاشت
    1.05
    teaching
    1.03
    TPS
    1.02
     Jain
    1.02
    POSITIVE LOGITS
     booze
    4.01
     alcohol
    3.85
     whiskey
    3.84
     beer
    3.78
     liquor
    3.69
     whisky
    3.66
    酒
    3.62
     beers
    3.57
     Alcohol
    3.55
     alkohol
    3.53
    Activations Density 1.348%

    No Known Activations