© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
     INTE
    1.44
    :
    1.39
     masuk
    1.33
     girlfriend
    1.33
    mrow
    1.31
     boyfriend
    1.23
    :<
    1.23
    /
    1.20
     போக
    1.20
     boundedness
    1.20
    POSITIVE LOGITS
     ð
    1.43
    атр
    1.40
    ير
    1.40
    ⃘
    1.32
    ном
    1.31
    ಝ
    1.31
     elas
    1.30
     cani
    1.29
    ড
    1.29
    час
    1.29
    Activations Density 0.050%

    No Known Activations