© 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. 101689
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in code

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

    closing parentheses in code, particularly after function calls or method invocations.

    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
    both
    -2.55
    during
    -2.36
     delightfully
    -2.33
    轳
    -2.27
    
    -2.19
    having
    -2.08
    dzić
    -2.06
    providedIn
    -2.05
    medriver
    -2.05
    within
    -2.03
    POSITIVE LOGITS
    ↵↵
    3.08
    ");
    2.53
    );
    2.39
    );
    
    2.16
    '];
    1.98
    e
    1.98
    </h2>
    1.97
    ());
    1.95
     because
    1.94
     even
    1.92
    Activations Density 0.083%

    No Known Activations