© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    formatting specifiers

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

    formatting specifiers and placeholders in code (like printf format strings, template variables, and similar syntax patterns).

    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
    --
    -1.75
     Agustus
    -1.73
    sssss
    -1.68
    -
    -1.68
    *</
    -1.66
    🤨
    -1.65
    😱
    -1.63
    !$
    -1.63
     剤
    -1.63
    婓
    -1.62
    POSITIVE LOGITS
    咐
    1.52
     poderos
    1.48
     soo
    1.45
    ्ड
    1.41
     lack
    1.41
    跟你
    1.41
    图源
    1.39
     некоторы
    1.39
     она
    1.38
     bildet
    1.38
    Activations Density 0.003%

    No Known Activations