© 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-16K
    7. 2091
    Prev
    Next
    INDEX
    Explanations

    division and equality

    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_16k_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
     smack
    3.08
    alış
    2.84
    ្នែក
    2.83
     empieza
    2.81
    ⿺
    2.75
     vực
    2.70
     irá
    2.68
    zelfde
    2.66
     vuelve
    2.65
     irão
    2.64
    POSITIVE LOGITS
    $('
    3.29
    й
    3.28
    ve
    3.21
    على
    3.21
    页面存档备份
    3.19
    tained
    3.12
    $('.
    3.02
    𝙞
    3.00
    dehyde
    2.95
    cknowled
    2.90
    Activations Density 0.502%

    No Known Activations