© 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. 22-GEMMASCOPE-RES-131K
    7. 25020
    Prev
    Next
    INDEX
    Explanations

    URL paths

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﱠ
    -1.37
    ikusbot
    -1.06
     znaleźć
    -0.99
    着脸
    -0.99
     společnost
    -0.98
    roughs
    -0.97
     flesta
    -0.96
    ～。
    -0.95
     who
    -0.95
     this
    -0.94
    POSITIVE LOGITS
    Leírás
    1.33
    注意事
    1.23
     recens
    1.20
     sice
    1.20
     conclud
    1.20
    
    1.19
     sodio
    1.16
    معرفی
    1.15
    (^_^
    1.13
     ater
    1.13
    Activations Density 0.003%

    No Known Activations