© 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. 970
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and operations

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

    The neuron is looking for numeric tokens (numbers) in mathematical 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
     rightful
    0.57
     signatory
    0.55
     promulg
    0.54
     territor
    0.54
    🏬
    0.54
    ຕ້ອງ
    0.54
    はもちろん
    0.54
     conformidad
    0.54
     prerog
    0.53
     privati
    0.52
    POSITIVE LOGITS
    4
    0.83
    5
    0.79
    3
    0.76
    2
    0.71
    sqrt
    0.70
    cosx
    0.69
     $-
    0.68
    ax
    0.67
    6
    0.66
    {-
    0.64
    Activations Density 0.009%

    No Known Activations