© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    await, if, display

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

    The neuron strongly activates on snippets of computer code (e.g. programming statements, assignments, object property accesses, and other code‐style tokens).

    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
    function
    0.66
     function
    0.63
    addEventListener
    0.58
    assert
    0.57
     Function
    0.57
     +=
    0.55
     '+':
    0.55
     System
    0.55
     &=
    0.53
     함수
    0.53
    POSITIVE LOGITS
     calculate
    0.89
     updating
    0.87
    updating
    0.84
    calculate
    0.83
     actualizar
    0.81
     calculates
    0.80
     elaborar
    0.80
     собрать
    0.80
     assemble
    0.80
     populate
    0.80
    Activations Density 0.001%

    No Known Activations