© 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. 453
    Prev
    Next
    INDEX
    Explanations

    foreign languages and entities

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

    This neuron activates on proper nouns—names of people, organizations, places, etc.

    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
     be
    0.32
     become
    0.31
    _
    0.29
     becomes
    0.28
     [
    0.27
     appear
    0.26
     (
    0.26
     contain
    0.26
     behave
    0.26
    0.26
    POSITIVE LOGITS
    希望
    0.29
     muốn
    0.29
    ließlich
    0.28
     ઉપરાંત
    0.28
     також
    0.27
     imagining
    0.27
     ankaŭ
    0.27
     인터넷
    0.27
     hypothes
    0.26
    зен
    0.26
    Activations Density 0.494%

    No Known Activations