© 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. 9788
    Prev
    Next
    INDEX
    Explanations

    global pass rate

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

    Keywords followed by details/structure

    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
     如何
    0.54
    藿
    0.51
    氇
    0.51
     luft
    0.49
    徂
    0.49
    ιν
    0.49
    孩子
    0.49
    如何
    0.48
    耒
    0.48
    怎么
    0.47
    POSITIVE LOGITS
     exporters
    0.49
    os
    0.49
    *
    0.46
     програм
    0.46
     adhesives
    0.45
    u
    0.43
     proponents
    0.43
     कृपा
    0.43
    .}}
    0.42
    の研究
    0.41
    Activations Density 0.000%

    No Known Activations