© 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. 30119
    Prev
    Next
    INDEX
    Explanations

    dress and gown descriptions

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

    This neuron responds to descriptive fashion and attire phrases, especially vivid clothing details (e.g. color, fabric, style) at events.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Hãy
    -0.87
    Thunk
    -0.82
     summer
    -0.79
    Lig
    -0.79
     operation
    -0.78
    zeń
    -0.78
    actable
    -0.75
     وي
    -0.75
    operation
    -0.75
     Lig
    -0.74
    POSITIVE LOGITS
     gown
    1.74
     gowns
    1.63
     dress
    1.19
    gown
    1.16
     evening
    1.09
     mermaid
    1.09
     dresses
    1.05
     Gown
    1.04
     custom
    1.00
    Atelier
    0.95
    Activations Density 0.016%

    No Known Activations