© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70004
    Prev
    Next
    INDEX
    Explanations

    anti particle annihilation

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

    The neuron detects LaTeX “bar” notation marking antiparticles (e.g. b̄, τ̄, anti–quark, anti–top).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     jeweiligen
    -1.79
    1
    -1.62
    モテ
    -1.50
    尪
    -1.48
     regal
    -1.48
     gedacht
    -1.48
     entrambi
    -1.43
     gemeinsam
    -1.41
     geplant
    -1.40
    medes
    -1.40
    POSITIVE LOGITS
    ,  
    1.59
    ！（
    1.57
    𝐒
    1.54
    𝐇
    1.48
    }
    1.45
    {
    1.45
    💲
    1.42
     вересня
    1.40
    <0xEF>
    1.40
    ını
    1.38
    Activations Density 0.016%

    No Known Activations