© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6941
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

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

    The neuron is keyed to LaTeX‐style mathematical notation—particularly numeric tokens and math operators inside equations.

    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
    дву
    -0.96
     Př
    -0.94
    ]+$
    -0.94
    блю
    -0.90
     kommunik
    -0.88
     Pří
    -0.88
     Introducción
    -0.87
     Notícias
    -0.87
    OVO
    -0.87
    БИ
    -0.87
    POSITIVE LOGITS
     órgãos
    1.07
    学ぶ
    1.04
     dezelfde
    1.03
     ailing
    0.97
     gioia
    0.96
    相处
    0.96
     aident
    0.95
     отдельных
    0.94
     normalerweise
    0.92
     другая
    0.90
    Activations Density 0.021%

    No Known Activations