© 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. 1633
    Prev
    Next
    INDEX
    Explanations

    why did

    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
    ði
    0.55
     Consecutive
    0.54
     bền
    0.54
     모
    0.54
    اديه
    0.53
     سلم
    0.53
     doble
    0.51
     Nacional
    0.51
    ะนั้น
    0.51
    imo
    0.51
    POSITIVE LOGITS
    fts
    0.68
    高志森
    0.64
     сми
    0.62
    ayy
    0.62
    behav
    0.62
    axes
    0.61
    ஜ
    0.61
    avgs
    0.61
    गिन
    0.60
    tant
    0.60
    Activations Density 0.214%

    No Known Activations