© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    experiments, consideration, and enablement

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

    This neuron primarily activates on the copular verb “is.”

    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_24_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
    й
    0.79
    ré
    0.77
    mn
    0.76
    स
    0.76
    ny
    0.73
    ları
    0.71
    ó
    0.71
    ni
    0.71
    ب
    0.71
    ک
    0.70
    POSITIVE LOGITS
    )`,
    0.96
     negocios
    0.95
     negócios
    0.95
     бонусы
    0.91
     povos
    0.89
     kiosks
    0.88
     сроки
    0.87
    щением
    0.87
     militias
    0.86
    ᱗
    0.85
    Activations Density 0.000%

    No Known Activations