© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12584
    Prev
    Next
    INDEX
    Explanations

    garlic, stir, sauté

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

    The neuron fires on nouns naming specific items in enumerations—e.g. instruments, dishes, ingredients—often those that follow “such as” or appear in recipe‐style lists.

    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_31_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
     விசார
    0.78
    予測
    0.76
     previsão
    0.76
    ﻰ
    0.74
     پژوه
    0.68
     कपकेक
    0.68
     விசாரணை
    0.66
     وزار
    0.66
    留学
    0.66
     موقع
    0.65
    POSITIVE LOGITS
    就能
    0.67
     trot
    0.65
     bạc
    0.63
    麻
    0.63
    ंछ
    0.63
    깐
    0.63
    就可以
    0.62
    就可以了
    0.61
     बेचने
    0.61
     stool
    0.60
    Activations Density 0.114%

    No Known Activations