© 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. 34-GEMMASCOPE-RES-131K
    4. 107837
    Prev
    Next
    INDEX
    Explanations

    Dream Jewelry

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

    This neuron detects occurrences of closing curly braces (“}”) in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    )。
    -1.04
    );
    -1.02
     testCase
    -0.92
    ;
    -0.90
    kans
    -0.87
    ).
    -0.86
    一郎
    -0.86
    "];
    -0.85
    "};
    -0.84
                
    -0.83
    POSITIVE LOGITS
     factory
    1.05
    Factory
    0.95
     Factory
    0.90
     هر
    0.90
     gerichtet
    0.87
     Constructor
    0.86
    ernan
    0.85
    factory
    0.83
     această
    0.81
    Onder
    0.80
    Activations Density 0.002%

    No Known Activations