© 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-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11350
    Prev
    Next
    INDEX
    Explanations

    fig in programming or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ן
    3.46
    ियों
    3.35
    ם
    3.19
    री
    3.16
     ched
    3.10
    ل
    3.09
    kia
    3.06
     így
    3.06
    ى
    3.06
    ર
    3.00
    POSITIVE LOGITS
    ে
    4.03
    o
    4.02
    ो
    3.33
    ా
    3.25
    e
    3.07
    ein
    3.00
    یوں
    2.93
    ی
    2.90
    ueroa
    2.81
    irittura
    2.78
    Activations Density 0.002%

    No Known Activations