© 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. 92281
    Prev
    Next
    INDEX
    Explanations

    their decision

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

    each item

    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
     ప్ర
    0.49
     UCLA
    0.45
    '
    0.44
     trải
    0.43
    title
    0.42
    ري
    0.42
    官员
    0.42
     কোর্স
    0.41
     نخست
    0.41
    檢
    0.41
    POSITIVE LOGITS
    Increment
    0.50
     어린이
    0.48
    なのか
    0.46
     hert
    0.46
     Об
    0.44
     नाव
    0.44
     ประเภท
    0.44
     sawing
    0.44
    ear
    0.44
    Internal
    0.43
    Activations Density 0.005%

    No Known Activations