© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 6834
    Prev
    Next
    INDEX
    Explanations

    equality checks

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

    The neuron detects numeric constants used in comparison or equality expressions in code (e.g., “== 0”, “>= threshold”, “!= NULL”).

    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
    的不同
    0.68
    Having
    0.65
    }};
    0.65
    if
    0.64
    PropTypes
    0.64
    ;;
    0.64
    если
    0.63
    ;
    0.63
    ();
    0.62
    Nature
    0.61
    POSITIVE LOGITS
     ""){
    1.27
     ''){
    1.22
     "":
    1.07
     '.')
    1.02
     "")
    1.00
     ){
    0.99
     '')
    0.98
     '':
    0.96
     '/')
    0.94
     ",")
    0.94
    Activations Density 0.007%

    No Known Activations