© 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. 5495
    Prev
    Next
    INDEX
    Explanations

    code comparison operators

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

    The neuron strongly activates on numeric tokens and comparison operators (e.g. loop counters, digits, and “<”), i.e. places where numbers are used in comparisons or iterative bounds.

    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
     ==
    1.19
    ==
    1.17
    ()==
    1.16
    )==
    1.09
    ]==
    1.09
    =='
    1.00
     =='
    0.98
    ]=="
    0.97
     ===
    0.96
    ']==
    0.95
    POSITIVE LOGITS
    <\
    0.93
     <
    0.87
    <(
    0.86
    ＜
    0.82
     ＜
    0.80
    <$
    0.79
    <{
    0.76
    )<\
    0.76
     $<\
    0.75
    <
    0.75
    Activations Density 0.013%

    No Known Activations