© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8564
    Prev
    Next
    INDEX
    Explanations

    end of code block

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

    The neuron is keyed to spotting backslash characters (i.e. “\”) that introduce LaTeX/math‐style expressions.

    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
     insulators
    0.65
    જનો
    0.64
    걍
    0.62
    лянчук
    0.59
     subsections
    0.59
    }<
    0.59
     consecutively
    0.59
    িল্প
    0.58
     limestone
    0.58
    の影響
    0.58
    POSITIVE LOGITS
    tif
    0.74
    nG
    0.71
    trusted
    0.71
    র
    0.71
    nV
    0.70
    t
    0.68
    tMap
    0.68
    nW
    0.67
    tat
    0.66
    tR
    0.66
    Activations Density 0.043%

    No Known Activations