© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5262
    Prev
    Next
    INDEX
    Explanations

    cycling, bike parts, and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     Pt
    0.87
    ▀
    0.78
     Presley
    0.78
     ██
    0.77
    Detroit
    0.76
     Elvis
    0.74
    Pt
    0.74
     Naruto
    0.73
     इमरान
    0.73
    ("<
    0.73
    POSITIVE LOGITS
     bike
    1.76
     bicycle
    1.60
     cycling
    1.60
    Bike
    1.59
     Bike
    1.57
     bikes
    1.55
     rider
    1.51
     riders
    1.50
     fiets
    1.47
     riding
    1.47
    Activations Density 0.088%

    No Known Activations