© 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. 34-GEMMASCOPE-RES-131K
    7. 25603
    Prev
    Next
    INDEX
    Explanations

    main function definition

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

    The neuron spikes on code tokens that introduce or invoke constructs with an opening parenthesis—e.g. function or macro calls like `return`, `array(`, `main(`, etc.

    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
    賃貸
    -0.82
     los
    -0.77
    クーポン
    -0.75
    </b>
    -0.75
     an
    -0.74
    qDebug
    -0.73
    
    -0.73
     providing
    -0.72
    滷
    -0.72
    </h5>
    -0.71
    POSITIVE LOGITS
    woorden
    0.94
     samti
    0.93
     steder
    0.91
    IContainer
    0.90
     confusing
    0.90
     respectivos
    0.90
     ciertamente
    0.88
    ouple
    0.86
    aze
    0.85
    ättä
    0.85
    Activations Density 0.057%

    No Known Activations