© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13840
    Prev
    Next
    INDEX
    Explanations

    unittest framework

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

    The neuron fires on occurrences of JUnit-related API identifiers and fully-qualified class or package names (e.g. “junit.framework.Test” or “junit.swing.ui.TestRunner”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     испыта
    0.61
     тести
    0.59
     tıkl
    0.58
    tested
    0.58
    騙
    0.57
     दूध
    0.57
     பயன்படுத்தி
    0.56
     besta
    0.56
    ंपूर्
    0.55
     ruch
    0.54
    POSITIVE LOGITS
    jupiter
    0.64
    Fix
    0.56
    修
    0.55
    Ignore
    0.54
    Tri
    0.53
    Assumption
    0.53
     Fix
    0.52
    éa
    0.51
    Maybe
    0.50
    若
    0.50
    Activations Density 0.002%

    No Known Activations