© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78229
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and definitions

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

    The neuron activates on LaTeX‐style mathematical notation—things like dollar signs, backslashes, math symbols, variable names, and equation fragments.

    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
     Trabalho
    -1.02
     персонал
    -0.94
     업
    -0.93
    klassi
    -0.92
    נְ
    -0.91
     ਲ
    -0.90
    :^{
    -0.90
    син
    -0.90
     Ди
    -0.88
    setChecked
    -0.87
    POSITIVE LOGITS
     convaincre
    0.99
     defied
    0.94
    ℃
    0.90
     سایر
    0.88
    čných
    0.88
     нещо
    0.87
    edakan
    0.84
    ツイート
    0.84
     huiles
    0.84
     ISSN
    0.83
    Activations Density 0.043%

    No Known Activations