© 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. 12699
    Prev
    Next
    INDEX
    Explanations

    format specifiers and string formatting

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

    The neuron is triggered by format‐string patterns in code (e.g. printf/fprintf calls or string literals containing “%” specifiers).

    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
    ($"
    0.61
    бері
    0.61
    랍니다
    0.58
     ={
    0.55
     التالية
    0.54
     Христос
    0.54
     Kuk
    0.53
     mahi
    0.53
    ریع
    0.52
    وهات
    0.51
    POSITIVE LOGITS
     "%
    1.57
     %
    1.47
    :%
    1.45
    [%
    1.35
    =%
    1.32
    ,%
    1.31
    %
    1.31
    '%
    1.30
     %.
    1.30
    "%
    1.29
    Activations Density 0.008%

    No Known Activations