© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    serve, cook, bake, roast

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

    This neuron detects imperative cooking-action verbs (e.g., stir, fry, mix, bake, serve) in recipe instructions.

    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
    Coroutine
    0.63
    чна
    0.62
    ции
    0.61
    filePath
    0.56
     +=
    0.55
     <=
    0.55
    عی
    0.55
    вак
    0.55
    hitung
    0.55
    goto
    0.54
    POSITIVE LOGITS
    鉭
    0.75
     arugula
    0.75
     pantry
    0.74
     deliciously
    0.73
     chutney
    0.71
     zucchini
    0.71
     với
    0.69
     unisex
    0.69
     foodie
    0.69
     stoneware
    0.69
    Activations Density 0.015%

    No Known Activations