© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on isolated proper names, trademarks, or branded product names.

    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
    거나
    0.64
    et
    0.61
     یا
    0.61
    u
    0.61
    ibul
    0.60
    cional
    0.59
    r
    0.59
    Ᏺ
    0.59
     или
    0.59
    w
    0.59
    POSITIVE LOGITS
     itse
    0.62
    巧妙
    0.58
     Tipps
    0.57
     ajuta
    0.57
    কাণ্ড
    0.57
     meskipun
    0.57
    कर्ताओं
    0.55
     নিজেও
    0.55
     diharapkan
    0.54
     tarda
    0.54
    Activations Density 0.528%

    No Known Activations