© 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. 235708
    Prev
    Next
    INDEX
    Explanations

    order or switches

    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
    ｻ
    0.52
    ೀತ
    0.49
     グラ
    0.48
     обсужда
    0.47
     aufgebaut
    0.46
     राघव
    0.46
     ここ
    0.46
     Оси
    0.46
     اوس
    0.46
     धमा
    0.45
    POSITIVE LOGITS
     Clothes
    0.49
     Christ
    0.47
    o
    0.46
     clothes
    0.45
    之际
    0.44
     whatnot
    0.44
     Times
    0.43
     Null
    0.43
    clothes
    0.43
     Provisional
    0.42
    Activations Density 0.001%

    No Known Activations