© 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. 3348
    Prev
    Next
    INDEX
    Explanations

    fashion and runway

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

    The neuron fires on mentions of fashion industry terminology and events (e.g. “fashion,” “catwalk,” “fashion show,” “fashion focus”), detecting when a text is discussing fashion-related topics.

    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
     kupa
    -0.84
    GEAR
    -0.79
     Cytometry
    -0.78
    FileSize
    -0.77
    ImageField
    -0.76
    ApiController
    -0.76
    üche
    -0.76
    ARIAN
    -0.74
    Hö
    -0.74
    WindowManager
    -0.74
    POSITIVE LOGITS
     runway
    3.47
     catwalk
    2.70
     runways
    2.36
     models
    2.08
     Runway
    1.99
    Models
    1.74
    models
    1.72
     modeling
    1.70
     Models
    1.67
     show
    1.66
    Activations Density 0.029%

    No Known Activations