© 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. 6908
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
    Perhaps
    -1.58
    as
    -1.53
    wicz
    -1.52
    Some
    -1.51
    ⚾
    -1.49
    Although
    -1.48
     saine
    -1.46
    After
    -1.43
    These
    -1.43
    Often
    -1.39
    POSITIVE LOGITS
     hefty
    1.51
    鼱
    1.48
     欣赏
    1.44
     damaligen
    1.42
    djang
    1.38
     conocido
    1.38
    recette
    1.36
     wundersch
    1.33
     [];
    1.32
    ובה
    1.31
    Activations Density 0.040%

    No Known Activations