© 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. 45721
    Prev
    Next
    INDEX
    Explanations

    categories of factors or types

    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
    鮰
    -1.89
    yship
    -1.82
    它们
    -1.78
    它的
    -1.78
     its
    -1.73
    ệu
    -1.70
     coupé
    -1.70
    another
    -1.69
    gencias
    -1.67
    なるべく
    -1.61
    POSITIVE LOGITS
     and
    1.89
     aspects
    1.57
     zwi
    1.52
     cepillo
    1.51
     impresionantes
    1.44
     cocinas
    1.38
     espectaculares
    1.38
     tantas
    1.38
     sebagainya
    1.38
     cejas
    1.38
    Activations Density 0.066%

    No Known Activations