© 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. 9274
    Prev
    Next
    INDEX
    Explanations

    either/or or both/and choices

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

    The neuron detects coordination phrases that link two (or more) items or parties—e.g. “both… and,” “simultaneous,” “those who.”

    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
    以外の
    0.64
    Autres
    0.63
     سایر
    0.61
    सबसे
    0.60
    ীদের
    0.59
    খের
    0.57
     እንኳ
    0.57
    অন্য
    0.57
     последние
    0.55
    জাতির
    0.55
    POSITIVE LOGITS
     zowel
    2.09
     både
    1.99
     sowohl
    1.95
     either
    1.95
     both
    1.94
    either
    1.92
     zarówno
    1.91
     سواء
    1.86
    both
    1.84
     Either
    1.77
    Activations Density 0.955%

    No Known Activations