© 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. 5493
    Prev
    Next
    INDEX
    Explanations

    luxury brands and items

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

    The neuron responds to tokens in fashion catalog–style product names and item titles (e.g. brand and clothing/accessory names in a listing).

    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
     cosplay
    0.85
     costumes
    0.72
     গার্ম
    0.71
     spandex
    0.68
    👙
    0.67
     cosmetology
    0.66
    👗
    0.66
    婼
    0.64
     outfits
    0.64
     গার্মেন্টস
    0.63
    POSITIVE LOGITS
     artisanal
    0.73
     Gucci
    0.73
    ヴィ
    0.72
     Comme
    0.69
     Maison
    0.68
     Chanel
    0.66
     グッチ
    0.66
     Burberry
    0.66
    珐
    0.65
     Collaboration
    0.64
    Activations Density 0.788%

    No Known Activations