© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79302
    Prev
    Next
    INDEX
    Explanations

    fashion and apparel industry

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

    The neuron spotlights mentions of fashion‐industry proper names and acronyms (e.g. “Fashion Institute of Technology,” “CFDA,” “Vogue Fashion Fund,” “fashion” in merchandising contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     women
    -0.76
    介入
    -0.74
    Urban
    -0.71
    信心
    -0.71
     Urban
    -0.69
    vene
    -0.68
     flor
    -0.67
     catalogue
    -0.66
     monos
    -0.66
    جموع
    -0.65
    POSITIVE LOGITS
     Fairchild
    0.98
     Cristóbal
    0.95
     Fiber
    0.87
     charme
    0.86
    Apparel
    0.83
     Lester
    0.82
     Apparel
    0.81
     Costume
    0.80
    weist
    0.80
     FID
    0.79
    Activations Density 0.039%

    No Known Activations