© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11660
    Prev
    Next
    INDEX
    Explanations

    This neuron detects mentions of splitting a list into halves for a recursive, divide-and-conquer sort.

    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
     равномер
    0.61
    刑
    0.60
    ホット
    0.56
    IQR
    0.55
     sphincter
    0.54
    Weyl
    0.54
    定位
    0.53
    噪
    0.53
    offsets
    0.52
    nrB
    0.52
    POSITIVE LOGITS
     DP
    1.06
     dp
    1.00
    dp
    0.90
    DP
    0.90
     recurs
    0.81
    Recurs
    0.80
    Dp
    0.80
     डीपी
    0.79
     memo
    0.79
     recursion
    0.79
    Activations Density 0.025%

    No Known Activations