© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6164
    Prev
    Next
    INDEX
    Explanations

    coffee and tea drinks

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

    The neuron detects mentions of beverages (especially coffee and tea).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ле
    0.68
     affluent
    0.64
    藏
    0.64
    цен
    0.59
    ECON
    0.59
    ायी
    0.59
     récol
    0.57
    PROC
    0.56
    ро
    0.56
     porcent
    0.56
    POSITIVE LOGITS
    ☕
    1.03
     Kaffee
    1.00
    🍪
    0.94
     Starbucks
    0.91
    Coffee
    0.89
     Caffeine
    0.86
     Coffee
    0.85
    🍵
    0.84
     caffè
    0.83
     entgegen
    0.83
    Activations Density 0.220%

    No Known Activations