© 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. 11993
    Prev
    Next
    INDEX
    Explanations

    function arguments/props

    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
    र
    3.07
    要
    2.83
    ist
    2.70
    ة
    2.57
    Һ
    2.51
     lain
    2.42
    જી
    2.42
    কালের
    2.37
    +}$
    2.35
    িত
    2.34
    POSITIVE LOGITS
    т
    3.60
    at
    3.36
    al
    3.09
    ب
    3.07
    an
    3.05
    r
    3.03
    р
    2.99
    m
    2.93
     Qxa
    2.91
    ्मी
    2.91
    Activations Density 0.026%

    No Known Activations