© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144983
    Prev
    Next
    INDEX
    Explanations

    standing time and instructions

    np_acts-logits-general · gemini-2.5-flash-lite

    unusual characters and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    0.48
    하거나
    0.48
    よく
    0.47
     দূরের
    0.46
    窗口
    0.45
    札
    0.44
    明
    0.43
    又は
    0.43
     타입을
    0.42
     cơ
    0.41
    POSITIVE LOGITS
    ،
    0.57
    für
    0.56
    dashed
    0.48
    twice
    0.48
    became
    0.48
    ពេលវេល
    0.48
    Ҥ
    0.47
    uasion
    0.47
    ਰ
    0.47
    iteration
    0.46
    Activations Density 0.001%

    No Known Activations