© 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. 117013
    Prev
    Next
    INDEX
    Explanations

    function callbacks

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

    The neuron fires on occurrences of function parameter names (especially common callback‐style identifiers like “action” or “callback”) in 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
     udang
    -0.91
     another
    -0.86
     condomínio
    -0.85
    داً
    -0.85
     kuh
    -0.84
    ilisation
    -0.84
    alte
    -0.82
     {
    -0.81
     undergo
    -0.81
     matang
    -0.80
    POSITIVE LOGITS
    函数
    1.02
     callable
    1.01
     func
    0.94
     funk
    0.93
    Функ
    0.92
    isFunction
    0.90
     dní
    0.87
     функция
    0.85
     mismo
    0.85
    vestido
    0.85
    Activations Density 0.029%

    No Known Activations