© 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. 9754
    Prev
    Next
    INDEX
    Explanations

    engine ignition or combustion

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

    The neuron fires on numeric measurement tokens—especially precise figures like decimals, ratios, and other technical numeric values.

    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
     axles
    0.66
     cuero
    0.64
     Stiffness
    0.59
     spinal
    0.58
     Peace
    0.57
    shoring
    0.57
     axle
    0.57
    ̪
    0.55
     Southport
    0.55
    把我
    0.54
    POSITIVE LOGITS
     fuel
    1.16
     carburetor
    1.16
     carbure
    1.14
    Fuel
    1.05
    燃料
    1.02
     연료
    1.01
     Fuel
    1.00
    fuel
    0.98
     ईंधन
    0.95
     combust
    0.95
    Activations Density 0.167%

    No Known Activations