© 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. 31-GEMMASCOPE-2-RES-16K
    4. 11002
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

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

    The neuron detects tokens representing floating‐point numbers (i.e. numeric strings containing a decimal point).

    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
    uccino
    0.56
    ágina
    0.54
    ड़े
    0.54
    HIB
    0.54
     típico
    0.52
     टास्क
    0.52
     prije
    0.50
    鉞
    0.50
    道的
    0.50
    ैनल
    0.49
    POSITIVE LOGITS
     exposures
    0.62
    hmm
    0.57
     vast
    0.56
    bid
    0.56
    RPM
    0.56
    ත්‍
    0.55
    shared
    0.55
     expos
    0.54
    ත්‍ර
    0.54
     RPM
    0.53
    Activations Density 0.116%

    No Known Activations