© 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. 11000
    Prev
    Next
    INDEX
    Explanations

    numbered lists

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

    The neuron activates on numeric expressions (quantities, prices, measurements, years, 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
     نیز
    0.62
     ও
    0.60
     एवं
    0.59
     cysts
    0.53
     and
    0.52
    也
    0.51
     (
    0.50
     và
    0.49
     nematode
    0.48
     و
    0.47
    POSITIVE LOGITS
    畀
    0.61
     allez
    0.59
    ر
    0.57
    wordpress
    0.57
    ianie
    0.57
    ದಯ
    0.57
    બસ
    0.56
    cmp
    0.55
     новых
    0.54
    か月
    0.54
    Activations Density 2.705%

    No Known Activations