© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12466
    Prev
    Next
    INDEX
    Explanations

    LaTeX math and code structures

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

    The neuron fires on capitalized content words—especially those forming titles or proper nouns.

    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
     ever
    0.59
    ////////////////
    0.57
    //
    0.56
     pract
    0.56
     />
    0.55
     riti
    0.54
     numbers
    0.54
    //////////////
    0.54
     but
    0.53
    (:
    0.52
    POSITIVE LOGITS
     ადგილ
    0.66
    তির
    0.61
    बंधनाच्या
    0.61
     温
    0.61
    úly
    0.60
    টাইমস
    0.59
    ଟ
    0.59
     სახელმწიფ
    0.59
     Revenues
    0.57
     بابەت
    0.57
    Activations Density 0.008%

    No Known Activations