© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6344
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

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

    The main thing this neuron does is find numeric tokens—especially numbers with decimal points.

    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_24_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
     एच
    0.49
    lazy
    0.45
    Dennis
    0.45
    ஜ
    0.43
    Lazy
    0.43
     discouraged
    0.43
    During
    0.42
     এইচ
    0.42
     woodwork
    0.42
    what
    0.41
    POSITIVE LOGITS
     descoper
    0.48
     gült
    0.48
    новни
    0.46
     জানিতে
    0.46
    ὖ
    0.44
     Vary
    0.43
    ostiene
    0.43
     вари
    0.43
     Unterschied
    0.42
    ărat
    0.42
    Activations Density 0.687%

    No Known Activations