© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34604
    Prev
    Next
    INDEX
    Explanations

    enumerations, tables, matrix, charts, timelines

    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
    Not in Any Lists

    No Comments

    Negative Logits
     swojego
    -0.96
    ,
    -0.95
    又不
    -0.94
     Grüßen
    -0.94
    Belgique
    -0.92
     wi
    -0.92
     laiko
    -0.90
    诙
    -0.90
     llegará
    -0.89
    的感覺
    -0.88
    POSITIVE LOGITS
    Ế
    1.23
     your
    1.06
    
    1.02
    StoryboardSegue
    0.99
     pstmt
    0.98
    raujo
    0.97
     LEYENDO
    0.97
    ровал
    0.97
     затруд
    0.97
    URLEncoder
    0.96
    Activations Density 0.121%

    No Known Activations