© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 537
    Prev
    Next
    INDEX
    Explanations

    questions about options or goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     autonomía
    0.66
     mesurer
    0.62
     Aloha
    0.62
     آموزشی
    0.61
     흐
    0.61
     mínima
    0.60
    الش
    0.60
     invester
    0.60
     власти
    0.59
     హ
    0.58
    POSITIVE LOGITS
     addition
    0.68
    addition
    0.68
    ermi
    0.63
    Addition
    0.61
     Addition
    0.59
     bonds
    0.57
     бер
    0.57
    combination
    0.57
     additions
    0.57
     Fifth
    0.56
    Activations Density 0.050%

    No Known Activations