© 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. 15828
    Prev
    Next
    INDEX
    Explanations

    JSON and code structure

    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
    ↵↵↵↵↵
    -1.81
    ↵↵↵↵
    -1.64
    1
    -1.63
     was
    -1.62
     Of
    -1.59
    ↵↵↵
    -1.58
     других
    -1.55
    ↵↵↵↵↵↵
    -1.51
    2
    -1.50
     by
    -1.46
    POSITIVE LOGITS
    آیا
    1.60
     bluz
    1.52
    ⁉
    1.51
    ♀
    1.49
    ==============
    1.45
    وقتی
    1.44
    ícias
    1.43
     stadion
    1.41
    stande
    1.41
    ‍♀️
    1.40
    Activations Density 0.001%

    No Known Activations