© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23451
    Prev
    Next
    INDEX
    Explanations

    as or equivalents

    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
    老的
    0.38
    ス
    0.38
    لاس
    0.37
     требуется
    0.37
    АС
    0.36
     تعمل
    0.36
     murió
    0.35
    ص
    0.35
     konnte
    0.35
     vigil
    0.35
    POSITIVE LOGITS
     sebagai
    1.79
     as
    1.51
     jako
    1.37
    作为
    1.35
    として
    1.34
     Sebagai
    1.33
     ως
    1.30
     као
    1.30
    作為
    1.22
    Sebagai
    1.20
    Activations Density 0.003%

    No Known Activations