© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7711
    Prev
    Next
    INDEX
    Explanations

    equations with variables and implications

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

    The neuron selectively activates on numeric tokens—particularly multi‐digit and 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
     Figure
    0.70
     $=\
    0.69
     :=
    0.68
     inductive
    0.68
     =
    0.68
     ×
    0.67
     algorithm
    0.67
     method
    0.66
     subtraction
    0.66
     $=$
    0.66
    POSITIVE LOGITS
    Leftrightarrow
    0.94
    <=>
    0.82
    ⇔
    0.79
    fetchAll
    0.76
    
    0.75
    (*)
    0.70
     তখনই
    0.68
     तभी
    0.65
     Đến
    0.63
    bookings
    0.62
    Activations Density 0.008%

    No Known Activations