© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51174
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes

    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/layer_40_width_65k_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
    -
    0.34
    ថ្
    0.34
    vál
    0.34
     بودن
    0.33
    ün
    0.33
     compañías
    0.32
    ｗ
    0.32
    лое
    0.32
    ੰ
    0.31
    Ｏ
    0.31
    POSITIVE LOGITS
     సాహిత
    0.36
    INGRE
    0.35
     अंत
    0.35
     כבר
    0.33
     вершин
    0.33
     விட
    0.33
    тового
    0.33
     ANTON
    0.32
    猀
    0.32
    setBackground
    0.31
    Activations Density 0.115%

    No Known Activations