© 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. 90472
    Prev
    Next
    INDEX
    Explanations

    motorsports, racing, riders, and bikes

    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
    司机
    -1.10
     car
    -1.08
     драй
    -0.99
    Cars
    -0.98
     Cars
    -0.94
    ドライバー
    -0.94
    开车
    -0.93
     driver
    -0.90
     cars
    -0.90
    Driver
    -0.90
    POSITIVE LOGITS
     motorcycle
    2.17
     bike
    2.02
     rider
    1.98
     riders
    1.88
     Motorcycle
    1.86
     motorcycles
    1.86
    bike
    1.82
     bikes
    1.80
     riding
    1.80
     Yamaha
    1.76
    Activations Density 0.096%

    No Known Activations