© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11542
    Prev
    Next
    INDEX
    Explanations

    This neuron detects non-linguistic page structure and navigation tokens (e.g. arrows, section headings, special symbols, and markup cues) rather than normal text.

    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
    nosed
    1.23
     elems
    1.20
    bandSize
    1.09
     cosines
    1.07
    َة
    1.05
    "]').
    1.05
    даги
    1.03
    𝄞
    1.03
    нинг
    1.02
    [,,"
    1.02
    POSITIVE LOGITS
    om
    1.63
    س
    1.52
    ل
    1.34
    و
    1.33
    תה
    1.29
    ো
    1.27
    ot
    1.26
    ו
    1.22
    ה
    1.21
    ز
    1.20
    Activations Density 5.019%

    No Known Activations