© 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. 232547
    Prev
    Next
    INDEX
    Explanations

    board membership and voting

    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
    icates
    0.47
    രള
    0.46
     hafta
    0.46
    ुस्तान
    0.45
    かわ
    0.44
    ゐ
    0.44
    zeros
    0.43
    filters
    0.43
     fere
    0.43
    ből
    0.43
    POSITIVE LOGITS
     brunâtre
    0.52
    RW
    0.52
     pertumbuhan
    0.49
     程序
    0.48
     RI
    0.47
    𝙽
    0.46
     czł
    0.46
     অগ্রগতি
    0.46
    URCH
    0.45
     অভিনন্দন
    0.45
    Activations Density 0.000%

    No Known Activations