© 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. 114131
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    ſelves
    -1.88
     tocado
    -1.74
    焄
    -1.67
    Наталья
    -1.66
     mág
    -1.66
    ၟ
    -1.66
     servido
    -1.65
    Слайд
    -1.65
     conocía
    -1.63
    ”:
    -1.63
    POSITIVE LOGITS
    '
    1.90
    .
    1.84
     is
    1.72
     '
    1.70
    /
    1.59
    ;
    1.51
    1
    1.31
    [
    1.30
     are
    1.27
     
    1.27
    Activations Density 0.097%

    No Known Activations