© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36442
    Prev
    Next
    INDEX
    Explanations

    QCD

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

    This neuron spots specialized high-energy physics terminology—particularly acronyms and jargon related to quantum chromodynamics (e.g. “QCD,” “gg”) and advanced concepts like “small transverse momentum” and “next‐to‐leading‐order.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sereia
    -1.52
     The
    -1.34
     bague
    -1.30
    哧
    -1.26
    ).
    -1.24
    </td>
    -1.22
     circonstances
    -1.21
     السياس
    -1.19
    鮰
    -1.17
     vía
    -1.16
    POSITIVE LOGITS
     first
    1.50
    Гц
    1.49
    🧫
    1.37
     averse
    1.33
     escuchadas
    1.30
     thunderstorms
    1.25
    entierung
    1.24
     will
    1.23
    viste
    1.22
     intricacies
    1.22
    Activations Density 0.019%

    No Known Activations