© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84439
    Prev
    Next
    INDEX
    Explanations

    fashion industry, brands, designers

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

    This neuron fires on occurrences of the word “fashion” (and its morphological variants, e.g. in “fashionista”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蹕
    -2.77
    荦
    -2.58
    .";
    -2.50
    の詳細
    -2.44
     publico
    -2.39
    の概要
    -2.34
    厯
    -2.30
    昞
    -2.23
     firmado
    -2.22
    uties
    -2.17
    POSITIVE LOGITS
    .
    3.97
    5
    2.80
    ”
    2.77
    ↵
    2.47
    Y
    2.45
    g
    2.28
    ve
    2.20
    6
    2.16
    4
    2.14
     Offering
    2.08
    Activations Density 0.007%

    No Known Activations