© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1280
    Prev
    Next
    INDEX
    Explanations

    DeepMind, Trevor Project

    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
    缶
    0.67
     efficiently
    0.65
    AntiForgery
    0.63
    ొక్క
    0.62
    Household
    0.61
    Efficient
    0.61
    ổng
    0.60
    дума
    0.60
     Cinque
    0.59
    仁
    0.59
    POSITIVE LOGITS
    bl
    0.67
     Bl
    0.66
     bl
    0.64
    idamente
    0.63
    Bl
    0.62
     Blair
    0.60
     ws
    0.59
     Lob
    0.57
     шанс
    0.57
    loops
    0.57
    Activations Density 0.258%

    No Known Activations