© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 58447
    Prev
    Next
    INDEX
    Explanations

    format specifiers like %d %s %c

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    <unused26>
    0.40
    <unused71>
    0.40
     Kershaw
    0.39
    ונה
    0.39
     महत्त्व
    0.39
    tempo
    0.37
    ﺴ
    0.36
     prey
    0.36
    rivate
    0.35
     mát
    0.35
    POSITIVE LOGITS
    ^[
    0.41
     phosphoric
    0.36
     //[
    0.36
    uad
    0.36
     дея
    0.35
    uluk
    0.35
     областях
    0.35
     ультра
    0.35
    зино
    0.34
     முயற்
    0.34
    Activations Density 0.000%

    No Known Activations