© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10249
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    Programming code syntax, particularly operators and punctuation used in code statements (such as parentheses, operators, method calls, and property access).

    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
    </h2>
    -1.61
    );
    
    
    -1.55
    <bos>
    -1.52
    ↵
    -1.46
    don
    -1.45
    ;">
    
    -1.45
     ''
    
    -1.44
    -1.38
    antMatchers
    -1.37
    有不少
    -1.35
    POSITIVE LOGITS
     these
    1.86
     this
    1.80
     each
    1.73
     those
    1.68
     знают
    1.64
     делают
    1.55
     their
    1.52
     cyclisme
    1.52
     akku
    1.52
     خواهد
    1.44
    Activations Density 0.273%

    No Known Activations