© 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. 13928
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    The neuron strongly activates on numeric tokens (especially decimal numbers) 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_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
     :)
    0.72
    !!
    0.70
    !
    0.68
    ✌
    0.67
     :-)
    0.66
    !”
    0.65
    unched
    0.64
     😊
    0.64
    !!!
    0.63
     ✨
    0.63
    POSITIVE LOGITS
     but
    1.37
     mutta
    1.24
     ولكن
    1.18
     But
    1.17
    でしたが
    1.17
     لیکن
    1.14
     لكن
    1.14
    但在
    1.13
    但是我
    1.13
    but
    1.13
    Activations Density 0.456%

    No Known Activations