© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83987
    Prev
    Next
    INDEX
    Explanations

    parenthetical roles and features

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

    offers regulation and design

    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
     zio
    0.53
     Mub
    0.49
     techno
    0.49
     Terra
    0.49
     Mutt
    0.49
     Duss
    0.48
     Armada
    0.47
    玠
    0.47
     Magde
    0.47
     Mö
    0.47
    POSITIVE LOGITS
    แข่งขัน
    0.53
    fourth
    0.50
    approved
    0.49
     প্রকৃত
    0.49
    entry
    0.48
     unlicensed
    0.48
    alem
    0.47
    alit
    0.47
     élytres
    0.46
    जेट
    0.46
    Activations Density 0.000%

    No Known Activations