© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13397
    Prev
    Next
    INDEX
    Explanations

    physical activities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    Serum
    0.52
     Pinnacle
    0.51
     ترم
    0.51
    スープ
    0.51
     হিন
    0.50
    禹
    0.50
    ⎤
    0.48
    newtheorem
    0.48
     шриф
    0.48
    
    0.47
    POSITIVE LOGITS
     bicycle
    4.56
     bike
    4.44
     biking
    4.22
     bicycl
    4.22
     Bike
    4.19
     Bicycle
    4.16
     bicycles
    4.09
     велосипе
    4.09
    自行车
    4.06
     bikes
    4.03
    Activations Density 0.170%

    No Known Activations