© 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. 2127
    Prev
    Next
    INDEX
    Explanations

    precise detail

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

    The neuron detects UI‐style instructions for browsing or viewing image/product galleries (e.g. “select another style in the above table,” “browse our entire collection,” “click the image above to see the full-size photo”).

    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
     ទ
    0.62
     arXiv
    0.56
     Drinfeld
    0.55
     Vascular
    0.55
    riert
    0.54
     対応
    0.54
    𒃲
    0.54
     एयर
    0.54
     バッグ
    0.54
     veille
    0.54
    POSITIVE LOGITS
    猥
    0.69
    jus
    0.57
    jt
    0.57
     fade
    0.55
    直至
    0.55
    ↵↵
    0.55
     roj
    0.54
     painted
    0.53
     faded
    0.53
     paint
    0.52
    Activations Density 0.000%

    No Known Activations