© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5627
    Prev
    Next
    INDEX
    Explanations

    `new` array or collection

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

    The neuron is looking for programming‐style identifiers or variable/function names (i.e. code tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =[]
    0.70
    ([]);
    0.65
    =[];
    0.65
     Bundan
    0.58
     []
    0.55
     [],
    0.55
    ([])
    0.54
    =[],
    0.53
     Sparrow
    0.53
     ከዚያ
    0.52
    POSITIVE LOGITS
    array
    0.92
     array
    0.87
     arrayOf
    0.76
     intArray
    0.63
    arrayOf
    0.61
     new
    0.61
     "{
    0.59
    new
    0.57
    司
    0.57
     Array
    0.57
    Activations Density 0.004%

    No Known Activations