© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15064
    Prev
    Next
    INDEX
    Explanations

    code comments or separators

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

    The neuron strongly activates on the “#” token used to introduce comments or directives in code.

    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_24_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
    lovers
    0.80
    phic
    0.79
    ）：
    0.79
    ，「
    0.77
    だ
    0.77
    ），
    0.76
    লে
    0.75
    。「
    0.75
    بیه
    0.75
    OS
    0.75
    POSITIVE LOGITS
     noqa
    1.02
    LoginActivity
    0.91
     అంత
    0.90
    bP
    0.89
    мб
    0.86
    кем
    0.86
    CartVO
    0.86
     이건
    0.84
    fZ
    0.84
    getBy
    0.83
    Activations Density 0.000%

    No Known Activations