© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    er
    3.46
    ার
    2.86
    в
    2.83
    ViewSet
    2.82
    ená
    2.72
     [&](
    2.72
    ే
    2.69
    eram
    2.66
    therapy
    2.64
    া
    2.51
    POSITIVE LOGITS
    unstyled
    3.41
    ENER
    3.25
    Selon
    3.14
    कालय
    3.02
     upravo
    2.99
    tener
    2.93
     phút
    2.88
     dụ
    2.67
     Harga
    2.64
     Người
    2.63
    Activations Density 0.379%

    No Known Activations