© 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. 11908
    Prev
    Next
    INDEX
    Explanations

    code or math sequences

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

    whitespace characters, particularly spaces and newlines in structured text like code and data files.

    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
     понравился
    -1.37
    président
    -1.34
    only
    -1.28
    我们是
    -1.26
     aimez
    -1.26
    鼱
    -1.25
     geschikt
    -1.23
    很赞
    -1.23
     каком
    -1.22
    だそうです
    -1.21
    POSITIVE LOGITS
    】：
    1.34
     Département
    1.30
    ☹
    1.27
    ↵
    1.26
    MigrationBuilder
    1.25
    phile
    1.19
    ⤵
    1.19
    lative
    1.19
     منذ
    1.19
    neous
    1.19
    Activations Density 0.054%

    No Known Activations