© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9846
    Prev
    Next
    INDEX
    Explanations

    invoke action

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

    The neuron fires on the verb “invoke” (in any casing), whether as a method name or plain text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    0
    -3.03
    five
    -2.94
     we
    -2.72
    蠖
    -2.72
    four
    -2.67
    2
    -2.67
    {
    -2.63
    </h1>
    -2.58
    廕
    -2.58
    enablog
    -2.56
    POSITIVE LOGITS
    
    2.84
    銫
    2.70
     巧克力
    2.47
    اسف
    2.41
    韞
    2.36
    愎
    2.36
     However
    2.36
    錞
    2.33
     肖像
    2.33
     There
    2.33
    Activations Density 0.003%

    No Known Activations