© 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. 10824
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols

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

    The neuron is specialized to spot floating‐point numeric values (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_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
     months
    0.55
    flo
    0.53
     {}>,
    0.53
    months
    0.53
    quer
    0.52
     ba
    0.51
     get
    0.49
    do
    0.49
    ktops
    0.49
     μην
    0.49
    POSITIVE LOGITS
     NSP
    0.62
    UNIVERSITY
    0.58
    NAMESPACE
    0.56
    𒉈
    0.55
     Caves
    0.55
     Grundlagen
    0.54
    Cave
    0.54
     vielfält
    0.54
     Reuse
    0.54
     peculiarities
    0.53
    Activations Density 0.000%

    No Known Activations