© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64805
    Prev
    Next
    INDEX
    Explanations

    drinking beverages

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

    The neuron fires on words referring to drinking or specific beverages (e.g. “drinking,” “drank,” “punch,” “wine,” “beer,” “cocktails”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    饮
    -0.94
     grid
    -0.84
    飲み
    -0.80
     drinkers
    -0.77
     drank
    -0.76
    GRID
    -0.75
    飲
    -0.75
     drenched
    -0.73
     drinking
    -0.73
    蝋
    -0.71
    POSITIVE LOGITS
     wine
    2.52
     beer
    2.45
     coffee
    1.88
     Wine
    1.75
    Wine
    1.70
     Beer
    1.66
    Beer
    1.66
     whiskey
    1.63
     champagne
    1.63
    beer
    1.59
    Activations Density 0.048%

    No Known Activations