© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on programming identifiers—especially Java class, package, and method names (e.g. “junit.framework.TestRunner.main”).

    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
    зон
    0.59
    zIndex
    0.55
     vibhav
    0.53
    actionBar
    0.52
    뵈
    0.52
     ruth
    0.51
    खोरी
    0.51
    ޑ
    0.51
    бовать
    0.50
     ساح
    0.50
    POSITIVE LOGITS
     Runner
    0.86
    RunWith
    0.86
    Runner
    0.84
     run
    0.83
     runner
    0.82
     Run
    0.78
     RUN
    0.78
     runners
    0.75
     runs
    0.75
    run
    0.70
    Activations Density 0.023%

    No Known Activations