© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3482
    Prev
    Next
    INDEX
    Explanations

    particle physics and fundamental forces

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

    The neuron strongly activates on scientific and technical terms—especially physics jargon, experimental apparatus, exotic particles, measurements, and related numerical data.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ⛹
    0.68
    🕘
    0.63
     Capita
    0.62
     обез
    0.61
     Basketball
    0.61
     баскетбол
    0.61
    Basketball
    0.60
    🕜
    0.59
    🏀
    0.58
    🕚
    0.57
    POSITIVE LOGITS
     quark
    1.38
     TeV
    1.29
     hadronic
    1.25
     quarks
    1.24
    TeV
    1.24
     electroweak
    1.22
     lepton
    1.21
     hadron
    1.20
     QCD
    1.20
     hadrons
    1.20
    Activations Density 0.031%

    No Known Activations