© 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. 8726
    Prev
    Next
    INDEX
    Explanations

    sometimes

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

    The neuron fires on descriptions of inefficient or flawed implementations—especially critiques of unoptimized patterns (e.g., regex backtracking and performance issues).

    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
     wszyscy
    0.65
    所有的
    0.65
    应该是
    0.63
    全ての
    0.62
     semua
    0.61
     bütün
    0.60
    所有人
    0.59
     müsste
    0.59
     wszystkich
    0.57
    すべての
    0.57
    POSITIVE LOGITS
     sometimes
    5.06
    sometimes
    4.75
     parfois
    4.56
     Sometimes
    4.50
    Sometimes
    4.50
     иногда
    4.28
    有时
    4.09
     manchmal
    4.06
    有时候
    3.98
     Иногда
    3.94
    Activations Density 1.182%

    No Known Activations