© 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. 34-GEMMASCOPE-RES-131K
    7. 116090
    Prev
    Next
    INDEX
    Explanations

    Nike and athletic apparel

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    鯱
    -0.93
     Palmas
    -0.79
     Huddersfield
    -0.78
    ونس
    -0.75
    Bolivia
    -0.75
     Pexels
    -0.74
     Wanderers
    -0.73
    indeed
    -0.72
    alamy
    -0.72
    ⒌
    -0.72
    POSITIVE LOGITS
     Nike
    1.70
    Nike
    1.31
     swoosh
    1.17
     NI
    1.16
     Oregon
    1.14
     Zoom
    1.07
    nike
    1.02
    Oregon
    1.02
     Air
    0.99
     Beaver
    0.99
    Activations Density 0.030%

    No Known Activations