© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14432
    Prev
    Next
    INDEX
    Explanations

    food preparation and cooking

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

    The neuron detects numeric quantities and measurements (e.g. step numbers, ingredient amounts, times).

    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
    ミュニ
    0.93
     DPRD
    0.93
    🏛
    0.93
    が存在
    0.91
     cumplimiento
    0.88
     personenbez
    0.88
    🏭
    0.88
    🏢
    0.86
     giurid
    0.85
    🛰
    0.85
    POSITIVE LOGITS
     marinade
    1.82
     zucchini
    1.70
     saucepan
    1.59
     buttermilk
    1.58
     seasonings
    1.55
     butternut
    1.54
     caramel
    1.53
     cloves
    1.53
     rinsed
    1.53
     cuisson
    1.53
    Activations Density 1.272%

    No Known Activations