© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3066
    Prev
    Next
    INDEX
    Explanations

    O(n) notation and complexities

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

    The neuron detects Big‐O notation expressions (e.g. O(log n)).

    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_24_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
    娯
    0.75
    赚钱
    0.73
    お店
    0.73
     pensamientos
    0.73
    사는
    0.70
    成为了
    0.70
    專輯
    0.70
    สามารถ
    0.69
    同意
    0.68
    شركة
    0.68
    POSITIVE LOGITS
     quartic
    0.75
     ८
    0.74
     collisional
    0.72
     ۴
    0.70
     $|\
    0.68
     ^{
    0.68
     TeV
    0.66
     nDims
    0.66
     λ
    0.66
     dissipative
    0.66
    Activations Density 0.002%

    No Known Activations