© 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. 10-GEMMASCOPE-RES-131K
    7. 15775
    Prev
    Next
    INDEX
    Explanations

    i18n and locale translation

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     will
    -2.31
     can
    -2.13
    al
    -2.09
    
    -2.00
     represents
    -1.98
    涠
    -1.95
    Of
    -1.94
     igång
    -1.93
     which
    -1.91
    eration
    -1.90
    POSITIVE LOGITS
     нескольких
    2.19
     \
    2.03
     estrés
    1.99
    1
    1.92
     двух
    1.91
     jolly
    1.85
     作り方
    1.80
    Beskrivning
    1.80
     dismal
    1.79
    *
    1.77
    Activations Density 0.003%

    No Known Activations