© 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. 10943
    Prev
    Next
    INDEX
    Explanations

    RA, MA, SA, FA abbreviations

    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
    ों
    3.57
    न
    3.40
    nya
    3.33
    s
    3.19
    st
    3.12
    ときの
    2.98
    n
    2.97
    র
    2.92
    க்
    2.91
    ところ
    2.88
    POSITIVE LOGITS
    ে
    4.34
    e
    4.12
    े
    3.53
    er
    3.39
    ตรฐาน
    3.16
    ̊
    3.14
    ños
    3.09
    el
    3.01
    an
    2.86
    ed
    2.84
    Activations Density 0.076%

    No Known Activations