© 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. 238863
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
     ModInt
    0.54
    嗘
    0.52
     resultSet
    0.50
     situazioni
    0.50
    testAvg
    0.49
    TimeDict
    0.49
     ܗ
    0.49
     semplici
    0.48
     যাহ
    0.48
     문제는
    0.48
    POSITIVE LOGITS
    ;
    0.62
    、
    0.61
    ،
    0.49
    е
    0.49
    ，
    0.47
    in
    0.47
     physicochemical
    0.46
    /
    0.46
     ext
    0.45
    German
    0.45
    Activations Density 0.000%

    No Known Activations