© 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. 72125
    Prev
    Next
    INDEX
    Explanations

    New or North followed by place names

    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
     our
    -2.47
     one
    -1.64
     had
    -1.52
     two
    -1.52
     three
    -1.45
     it
    -1.41
     distintas
    -1.35
     enormous
    -1.34
     four
    -1.34
     what
    -1.32
    POSITIVE LOGITS
    
    1.48
     ulong
    1.39
    一股
    1.37
     trofeo
    1.36
     XCTest
    1.34
     nevada
    1.33
     xxiv
    1.33
    ку
    1.32
    こん
    1.31
    픈
    1.31
    Activations Density 0.072%

    No Known Activations