© 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. 10854
    Prev
    Next
    INDEX
    Explanations

    arrays and lists defined with parentheses

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

    The neuron activates on the literal PHP “array” keyword (i.e. occurrences of array-style declarations).

    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
     and
    -2.31
     votación
    -1.40
    lgari
    -1.38
     皮肤
    -1.30
     arşivlendi
    -1.30
     también
    -1.28
    コミュニ
    -1.27
    亶
    -1.26
    gupta
    -1.26
     大全
    -1.26
    POSITIVE LOGITS
    (
    1.70
    o
    1.64
    {
    1.55
     (
    1.51
    <em>
    1.46
    [
    1.46
    *
    1.45
    ,
    1.44
    /
    1.41
    -
    1.37
    Activations Density 0.001%

    No Known Activations