© 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. 86266
    Prev
    Next
    INDEX
    Explanations

    historical events and timing

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

    press release or api services

    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
    。
    0.49
    ။
    0.49
    ۔
    0.46
    ↵↵
    0.46
    ،
    0.46
     cuer
    0.45
     clavier
    0.45
     כ
    0.44
    。（
    0.44
     ،
    0.43
    POSITIVE LOGITS
     Historical
    0.52
     Historic
    0.51
     Mistakes
    0.49
     Timing
    0.49
     écrite
    0.48
    টের
    0.45
     Ridge
    0.45
     Discover
    0.45
     Postage
    0.44
     Simplifying
    0.44
    Activations Density 0.001%

    No Known Activations