© 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. 34-GEMMASCOPE-RES-131K
    7. 76977
    Prev
    Next
    INDEX
    Explanations

    uniform convergence

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

    The neuron is detecting LaTeX‐style mathematical notation (e.g. backslashes, math operators, environment commands, and math‐related vocabulary).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    argmin
    -0.79
    tershire
    -0.77
    buli
    -0.74
     ری
    -0.73
    ンダル
    -0.71
     nødven
    -0.69
    SCAN
    -0.68
    ffie
    -0.68
    oyant
    -0.66
     results
    -0.66
    POSITIVE LOGITS
     uniform
    1.80
    uniform
    1.77
     uniformly
    1.72
     Uniform
    1.66
    Uniform
    1.65
     uniforme
    1.47
    sup
    1.42
     sup
    1.31
     uniforms
    1.13
     uniformes
    1.11
    Activations Density 0.049%

    No Known Activations