© 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. 209
    Prev
    Next
    INDEX
    Explanations

    comma followed by two

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

    The neuron is keyed to mentions of global business/market contexts—tokens like “market,” “global,” “abroad,” and “New York” where international expansion or market size is discussed.

    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
    0.29
     の
    0.27
    ,
    0.26
    =
    0.26
     your
    0.25
     you
    0.25
    )
    0.25
    ()
    0.23
    の
    0.23
     there
    0.23
    POSITIVE LOGITS
    which
    0.42
    including
    0.37
     जिसमें
    0.37
     which
    0.36
    featuring
    0.36
    ซึ่ง
    0.36
     waarbij
    0.36
     incluindo
    0.35
     जिससे
    0.35
     जिनमें
    0.35
    Activations Density 1.597%

    No Known Activations