© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10090
    Prev
    Next
    INDEX
    Explanations

    bike and cycling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Honeywell
    0.82
     இஸ்
    0.73
     ООО
    0.68
     మాత్ర
    0.68
     playwright
    0.68
     হাজী
    0.68
     एयरपोर्ट
    0.68
    弇
    0.67
     теа
    0.67
    ოველ
    0.66
    POSITIVE LOGITS
     bike
    2.82
    Bike
    2.71
     bicycle
    2.68
     Bike
    2.63
     cycling
    2.61
     Cycling
    2.56
     cyclist
    2.56
     cyclists
    2.54
     bikes
    2.54
     Bicycle
    2.52
    Activations Density 0.091%

    No Known Activations