© 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. 165051
    Prev
    Next
    INDEX
    Explanations

    working together

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

    fit (or very close)

    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
     QUE
    0.44
    記得
    0.40
     nuestros
    0.39
     फ़रवरी
    0.39
    cigarettes
    0.38
    =");
    0.38
     રહી
    0.38
    ([^
    0.38
     Que
    0.38
    ((*
    0.37
    POSITIVE LOGITS
     Veterinary
    0.51
    🧙
    0.47
    🥋
    0.47
    铤
    0.46
    🧵
    0.46
     мое
    0.45
    했지만
    0.44
    但这
    0.44
     bitOp
    0.44
    损
    0.43
    Activations Density 0.000%

    No Known Activations