© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12466
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code snippets

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

    The neuron strongly activates on cooking‐procedure language—imperative kitchen actions and equipment terms (e.g. “whisk,” “cook,” “skillet,” “heat,” “crisp”).

    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
     Ведь
    0.66
     మరియు
    0.64
    อื่นๆ
    0.63
     Также
    0.59
     военной
    0.59
     !!
    0.56
    ClFN
    0.56
    욬
    0.56
     gesamten
    0.56
     Honourable
    0.56
    POSITIVE LOGITS
     inférieure
    0.61
     guère
    0.61
    thresh
    0.58
     দুটো
    0.57
     nong
    0.55
     légumes
    0.54
     a
    0.54
     সঙ্গে
    0.54
     four
    0.52
    trunc
    0.52
    Activations Density 0.042%

    No Known Activations