© 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. 79334
    Prev
    Next
    INDEX
    Explanations

    category theory concepts

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

    The neuron strongly fires on LaTeX‐style mathematical expressions and markup (e.g. dollar signs, mathcal, backslashes, and math tokens).

    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
     roots
    -0.81
     energy
    -0.79
    ciso
    -0.76
    cosas
    -0.76
    peen
    -0.73
    jay
    -0.73
    publisher
    -0.73
    ኩ
    -0.72
     Rückkehr
    -0.72
     acoustic
    -0.71
    POSITIVE LOGITS
     category
    1.86
     categories
    1.70
     Category
    1.64
    category
    1.53
    Category
    1.50
    categories
    1.44
     Categories
    1.39
    Categories
    1.34
     категории
    1.32
     catégorie
    1.30
    Activations Density 0.033%

    No Known Activations