© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56889
    Prev
    Next
    INDEX
    Explanations

    Cartesian product

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

    The neuron strongly activates on TeX/LaTeX markup tokens (in particular the backslash “\” that begins math commands).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    เน
    -0.85
    ondag
    -0.79
    素材
    -0.78
    meiras
    -0.77
     рослин
    -0.76
     Sketches
    -0.74
    COND
    -0.72
     approvals
    -0.71
     seniority
    -0.69
    capsulation
    -0.68
    POSITIVE LOGITS
     product
    2.00
     Cartesian
    1.95
    Cartesian
    1.63
     Product
    1.63
     cartesian
    1.62
    product
    1.56
    Product
    1.55
     direct
    1.46
     producto
    1.46
     products
    1.45
    Activations Density 0.059%

    No Known Activations