© 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. 54033
    Prev
    Next
    INDEX
    Explanations

    checking for array types

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

    This neuron detects calls to built-in type-checking functions (like is_array, is_object, Array.isArray, is_int).

    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
    ӟ
    -0.66
    Гра
    -0.66
    スパ
    -0.66
     Naturschutz
    -0.65
     Robbins
    -0.63
    hala
    -0.63
     pussy
    -0.63
    ưu
    -0.62
    现象
    -0.61
    HOC
    -0.61
    POSITIVE LOGITS
    美味しかった
    0.80
    植え
    0.74
    getOriginal
    0.73
    zeczytaj
    0.71
     rire
    0.70
     jovens
    0.70
     schaff
    0.70
     Gild
    0.69
    щества
    0.68
     방법
    0.68
    Activations Density 0.056%

    No Known Activations