© 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. 12742
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of formal academic or scientific fields, departments, and research‐related entity 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
     ents
    0.52
     lige
    0.50
     века
    0.47
     enlarged
    0.47
     namelijk
    0.47
     Shad
    0.45
    '`
    0.43
     demeanor
    0.43
    套装
    0.43
    锉
    0.43
    POSITIVE LOGITS
    ம்ம
    0.64
    เม
    0.56
    মে
    0.55
     unm
    0.54
     Megh
    0.54
    msch
    0.53
    انا
    0.51
    اسی
    0.50
    MeOH
    0.50
    菓子
    0.50
    Activations Density 0.559%

    No Known Activations