© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32635
    Prev
    Next
    INDEX
    Explanations

    ethnic clothing and textiles

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

    The neuron fires on mentions of specific fashion items, fabrics, brands, and designer‐related terms.

    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
     détru
    -0.95
    鞋
    -0.83
    キュリティ
    -0.81
    daille
    -0.80
     dispositivo
    -0.77
     formato
    -0.77
     device
    -0.76
     мощ
    -0.76
    面具
    -0.75
     Himalayan
    -0.74
    POSITIVE LOGITS
     ethnic
    1.29
     Ethnic
    1.03
     Kur
    1.02
     Dup
    1.01
    Ethnic
    0.99
    Dup
    0.95
     stitched
    0.94
     Meters
    0.93
     occasions
    0.91
     étn
    0.91
    Activations Density 0.025%

    No Known Activations