© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12427
    Prev
    Next
    INDEX
    Explanations

    cherry blossom

    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
    Negative Logits
    наче
    3.29
    ul
    3.13
    员
    2.76
    ता
    2.72
    м
    2.67
    었던
    2.65
    ى
    2.65
    е
    2.63
    খানেই
    2.60
    ă
    2.58
    POSITIVE LOGITS
    PURE
    3.34
    ‍♂️
    3.30
     говорится
    3.15
     yli
    3.12
     Tomatoes
    3.12
     indexRouter
    3.04
    艋
    3.04
     Định
    3.03
    酐
    3.00
    鈮
    2.96
    Activations Density 0.005%

    No Known Activations