© 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. 67570
    Prev
    Next
    INDEX
    Explanations

    data structures like list, array

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

    This neuron activates on names or mentions of sequence/collection types and constructors (e.g. List, Seq, Array, Set, listOf).

    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
     BEFORE
    -1.82
    轳
    -1.77
     antes
    -1.68
     verschiedene
    -1.67
     MUCH
    -1.66
    鏖
    -1.63
    聾
    -1.62
    .’”
    -1.61
    …’
    -1.60
     Vý
    -1.59
    POSITIVE LOGITS
    '
    1.99
    Doesn
    1.55
    鱨
    1.48
    ヒール
    1.45
     mélange
    1.41
     Hinblick
    1.39
    鸝
    1.38
    錞
    1.37
    2
    1.37
     anunciou
    1.35
    Activations Density 0.011%

    No Known Activations