© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5589
    Prev
    Next
    INDEX
    Explanations

    past or previous context

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

    The neuron activates strongly on numeric tokens formatted as floating‐point statistics (numbers with decimals).

    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
    h
    0.70
     entrees
    0.68
    Miscellaneous
    0.68
    NIE
    0.68
    a
    0.68
    ara
    0.67
    TX
    0.64
    AndTime
    0.64
    ="@
    0.64
    MVC
    0.64
    POSITIVE LOGITS
     沒有
    0.68
     여기가
    0.68
     fondamentali
    0.67
     ব্রিজ
    0.67
     Той
    0.66
     Бек
    0.65
     January
    0.64
     cái
    0.63
     读取
    0.63
    פט
    0.62
    Activations Density 0.001%

    No Known Activations