© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111362
    Prev
    Next
    INDEX
    Explanations

    closing curly brace

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

    closing braces in code that end an else block.

    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
    -1.55
     этого
    -1.48
     grotte
    -1.45
     både
    -1.33
     När
    -1.31
     této
    -1.30
     zarówno
    -1.28
    蹋
    -1.27
     logement
    -1.27
     sentier
    -1.26
    POSITIVE LOGITS
    ,”
    1.56
     —
    1.41
     (“
    1.38
    zation
    1.33
     古着
    1.30
    ють
    1.28
     nebst
    1.27
    楽しみにして
    1.26
     in
    1.26
     are
    1.24
    Activations Density 0.003%

    No Known Activations