© 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. 10688
    Prev
    Next
    INDEX
    Explanations

    emergency services

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

    The neuron activates on numeric tokens (especially decimal numbers) in the text, i.e. it detects measurements or other numeric expressions.

    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
     aberrant
    0.67
     ر
    0.64
     std
    0.63
     sixteen
    0.62
     Ø
    0.61
    entery
    0.60
     freg
    0.60
     deset
    0.59
     أ
    0.59
     இரண்டாவது
    0.59
    POSITIVE LOGITS
    Wildlife
    0.59
    Website
    0.57
    VN
    0.56
     تساعد
    0.55
    Ḩ
    0.55
    Possibly
    0.54
     동안
    0.54
     नाइन
    0.54
    naires
    0.54
    Waiting
    0.54
    Activations Density 0.181%

    No Known Activations