© 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. 10-GEMMASCOPE-RES-131K
    7. 102204
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML/XML attribute assignments, specifically the equals sign and quotation marks in attribute-value pairs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.49
     pareció
    -1.24
     algun
    -1.23
     dichiarato
    -1.21
     Terbaik
    -1.21
     Terbaru
    -1.20
    Liefer
    -1.16
    足够的
    -1.16
    最近の
    -1.16
    ées
    -1.14
    POSITIVE LOGITS
     that
    1.65
     גם
    1.34
    biendo
    1.34
    が行
    1.33
    ↵↵
    1.33
     dacă
    1.30
     și
    1.29
    multer
    1.27
     både
    1.27
    quered
    1.24
    Activations Density 0.116%

    No Known Activations