© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4298
    Prev
    Next
    INDEX
    Explanations

    bikes and bicycles

    np_acts-logits-general · gemini-2.5-flash-lite

    bikes and cycling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    劇場
    0.51
     dehuman
    0.47
     ಸಲ್ಲ
    0.47
    文字列
    0.47
    捜
    0.46
     autocratic
    0.45
    classAttribute
    0.45
    蠱
    0.45
     関数
    0.44
    substring
    0.44
    POSITIVE LOGITS
     bike
    1.74
     Bike
    1.67
     bicycle
    1.64
    Bike
    1.63
     bikes
    1.59
     Bicycle
    1.54
    自行车
    1.54
    bike
    1.52
     Bikes
    1.52
     велосипе
    1.52
    Activations Density 0.343%

    No Known Activations