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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80870
    Prev
    Next
    INDEX
    Explanations

    pages, page numbers

    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_34/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
    荼
    -0.78
     CEST
    -0.75
    ȴ
    -0.74
     weekday
    -0.71
    asso
    -0.71
    tissue
    -0.71
     GND
    -0.71
     seja
    -0.71
    PullParser
    -0.71
    
    -0.70
    POSITIVE LOGITS
     page
    2.59
     pages
    2.31
     Page
    2.19
    Page
    2.13
    page
    2.08
     PAGE
    2.06
    PAGE
    1.92
     Pages
    1.91
    ページ
    1.80
     paging
    1.78
    Activations Density 0.110%

    No Known Activations