© 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. 6654
    Prev
    Next
    INDEX
    Explanations

    `var` or `val` declarations

    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
    鲩
    -1.63
     .........
    -1.58
    躄
    -1.55
     Dinas
    -1.53
     .......
    -1.53
     reiter
    -1.52
    นี้
    -1.52
     ........
    -1.52
     realizada
    -1.50
    菒
    -1.47
    POSITIVE LOGITS
     devastating
    1.65
    囹
    1.55
    並み
    1.46
    とお
    1.46
     countless
    1.40
     ciudadana
    1.35
    大半
    1.34
    裏面
    1.34
     douleur
    1.34
     fört
    1.34
    Activations Density 0.012%

    No Known Activations