© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56780
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     खे
    -0.85
     felpa
    -0.79
    ované
    -0.73
     tričko
    -0.73
     不能
    -0.71
    Regist
    -0.71
    潤
    -0.70
     schermo
    -0.70
    muje
    -0.70
    Hammer
    -0.69
    POSITIVE LOGITS
    sqrt
    0.90
     SQ
    0.85
    pea
    0.78
    √
    0.78
    仕様
    0.77
     √
    0.77
    amsmath
    0.77
     Sq
    0.74
    第二个
    0.74
     DI
    0.73
    Activations Density 0.024%

    No Known Activations