© 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. 13172
    Prev
    Next
    INDEX
    Explanations

    programming keywords like set, run, each

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

    The neuron activates on programming API identifiers or method/function names (e.g. CamelCase calls like addLayer, removeLayer, setView, Application.Run, jQuery.each, Intent.createChooser).

    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
     we
    -1.32
     других
    -1.16
    enablog
    -1.04
     andere
    -1.02
    стта
    -1.00
     другие
    -0.98
     outras
    -0.98
    Werdegang
    -0.97
     其他
    -0.97
     ADDITIONAL
    -0.97
    POSITIVE LOGITS
     of
    1.92
    SRR
    1.09
     him
    1.09
    İM
    1.05
     són
    1.05
     ''){
    1.00
    Cevap
    1.00
    』。
    0.99
     inglese
    0.98
    Größe
    0.98
    Activations Density 0.010%

    No Known Activations