© 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. 22-GEMMASCOPE-RES-131K
    7. 104701
    Prev
    Next
    INDEX
    Explanations

    function declaration and callback

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

    The neuron fires on occurrences of “call” or “callback” (i.e. tokens that name or invoke callbacks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.08
    owels
    -0.96
     farklı
    -0.94
    tallet
    -0.91
    GRAFIA
    -0.89
    lila
    -0.87
    stacles
    -0.86
    pullover
    -0.85
    outube
    -0.85
    𝘨
    -0.85
    POSITIVE LOGITS
     this
    1.18
     masaje
    1.05
    ناق
    0.97
     zelo
    0.96
    NavigationBar
    0.95
     tatouage
    0.92
     themselves
    0.91
    vedra
    0.87
     Kapol
    0.87
     alegre
    0.87
    Activations Density 0.003%

    No Known Activations