© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10257
    Prev
    Next
    INDEX
    Explanations

    bor variants

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

    This neuron fires on occurrences of the proper name “Borussia” (and its subword fragments) in the 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_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
     Corps
    0.58
     contrary
    0.58
     末
    0.55
     Moors
    0.53
    orc
    0.52
     ganglia
    0.52
     Development
    0.52
     Prolong
    0.52
    պես
    0.52
    acağım
    0.51
    POSITIVE LOGITS
    Bor
    0.70
     Bor
    0.66
     بور
    0.65
     bore
    0.63
    硼
    0.60
     बोर
    0.59
    infinite
    0.59
    QA
    0.57
    بور
    0.57
    raron
    0.57
    Activations Density 0.185%

    No Known Activations