© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15980
    Prev
    Next
    INDEX
    Explanations

    functional programming Haskell monadic pipes

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

    This neuron detects numeric tokens—especially numerical values (both integers and floats) appearing 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_31_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
     sial
    0.57
     emozioni
    0.56
    瘧
    0.56
    ಿಸುತ್ತಾರೆ
    0.56
    GGA
    0.55
     सागरी
    0.55
    경상
    0.55
     sehen
    0.54
     ग्लैमर
    0.54
     Montenegro
    0.54
    POSITIVE LOGITS
     >>=
    0.97
     Maybe
    0.93
     Haskell
    0.87
     Just
    0.82
    Maybe
    0.81
     Prelude
    0.79
     λ
    0.77
     nonEmpty
    0.75
     monadic
    0.75
     <$>
    0.73
    Activations Density 0.017%

    No Known Activations