© 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. 1152
    Prev
    Next
    INDEX
    Explanations

    stirring, mixing, or tossing food

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

    The neuron activates on explicit quantitative expressions—numbers, measurements, counts, and units.

    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
     edific
    0.78
    躾
    0.76
     illetve
    0.76
     solamente
    0.75
    锺
    0.74
     ಹಾಗೂ
    0.73
     mathematic
    0.72
     peruse
    0.72
     pertaining
    0.70
     portrays
    0.70
    POSITIVE LOGITS
    uxi
    0.80
    Xia
    0.77
     ดังนั้น
    0.76
     Xia
    0.76
     weekdays
    0.73
    ！
    0.72
     Atención
    0.72
     후에
    0.71
    ："
    0.71
    ําน
    0.70
    Activations Density 0.076%

    No Known Activations