© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -1.87
    "../
    -1.78
     aquellas
    -1.78
     "..\..\
    -1.76
    TOBER
    -1.73
    iterranean
    -1.70
    ⅜
    -1.70
    appli
    -1.66
    ⅞
    -1.62
    terness
    -1.61
    POSITIVE LOGITS
     unquestionably
    1.63
    二日
    1.59
    a
    1.58
     touted
    1.54
     bonitas
    1.49
     aligning
    1.47
    优点
    1.45
     skillfully
    1.45
    最高の
    1.44
    Poznám
    1.44
    Activations Density 0.010%

    No Known Activations