© 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. 98692
    Prev
    Next
    INDEX
    Explanations

    relative paths before directory 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
    鬭
    -2.03
    鹟
    -1.87
     mey
    -1.80
     vijf
    -1.76
     cial
    -1.70
    っていると
    -1.66
    谗
    -1.66
     technische
    -1.65
     pretože
    -1.63
     interessante
    -1.63
    POSITIVE LOGITS
     includes
    2.30
     has
    1.76
     with
    1.70
     Only
    1.68
     will
    1.68
    !!!!!
    1.63
     truly
    1.63
     one
    1.62
     while
    1.60
     improves
    1.60
    Activations Density 0.008%

    No Known Activations