© 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. 111464
    Prev
    Next
    INDEX
    Explanations

    buying, selling, or changing terms

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

    lists, lectures, software, sources, where

    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
    il
    0.59
    いる
    0.55
    기
    0.54
    िलों
    0.49
    ίας
    0.48
    ν
    0.46
    िड
    0.46
    ن
    0.45
    น
    0.45
    học
    0.45
    POSITIVE LOGITS
     ไหร่
    0.52
     sprinkle
    0.47
     చక్ర
    0.46
     advises
    0.46
     projekt
    0.45
     eksper
    0.45
     කල
    0.44
     guarantees
    0.44
     บริษัท
    0.44
     burgundy
    0.43
    Activations Density 0.000%

    No Known Activations