© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58282
    Prev
    Next
    INDEX
    Explanations

    cross-country skiing

    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
    Motorcycle
    -0.83
    cropping
    -0.79
     Atari
    -0.77
    SEPT
    -0.76
    diving
    -0.75
     někdo
    -0.75
    itzar
    -0.73
    crops
    -0.73
    Chham
    -0.72
    fuls
    -0.72
    POSITIVE LOGITS
     ski
    1.18
     Nordic
    1.16
     groom
    1.07
     skiing
    1.06
     grooming
    1.05
     Ski
    1.02
     skis
    0.96
     trail
    0.95
     technique
    0.94
     Classical
    0.94
    Activations Density 0.022%

    No Known Activations