© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85747
    Prev
    Next
    INDEX
    Explanations

    Rac, Cort, Aldrich, pkg, Added

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

    code, identifiers, specific terms

    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
    Negative Logits
    老
    0.43
     makhluk
    0.42
     Kathleen
    0.42
     ngôn
    0.41
     Lili
    0.41
    傀
    0.40
     conoc
    0.39
    rebbero
    0.39
    괴
    0.39
     giết
    0.39
    POSITIVE LOGITS
    <0xE2>
    0.46
    Web
    0.41
    Doing
    0.41
    Dest
    0.39
    ∖
    0.39
    DO
    0.39
    feet
    0.39
    Legal
    0.38
     feet
    0.38
    CG
    0.38
    Activations Density 0.093%

    No Known Activations