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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86987
    Prev
    Next
    INDEX
    Explanations

    drinks and cocktails

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

    The neuron fires on specific mixed‐drink and cocktail names (e.g. Old Fashioned, Manhattan, Bloody Mary, Lemon Drop, punch, etc.).

    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
     urodz
    -0.78
     triste
    -0.74
    ':'
    -0.74
    岷
    -0.73
     corals
    -0.73
     franca
    -0.72
     aastal
    -0.71
     CLOS
    -0.71
     sola
    -0.70
    peutic
    -0.70
    POSITIVE LOGITS
     pitcher
    1.05
     pitchers
    0.92
     giù
    0.90
     drink
    0.88
     refresher
    0.88
     cocktails
    0.85
     Collins
    0.84
     mules
    0.84
     screwdriver
    0.83
     frozen
    0.81
    Activations Density 0.009%

    No Known Activations