© 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. 93740
    Prev
    Next
    INDEX
    Explanations

    gluon

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

    The neuron consistently lights up on dense, domain-specific scientific terminology—especially physics/math jargon in research abstracts.

    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
     Auto
    -0.68
    𝚁
    -0.68
     Bureau
    -0.68
    uza
    -0.68
    ief
    -0.66
     woda
    -0.65
    iant
    -0.64
    hematical
    -0.63
    ều
    -0.63
     lepton
    -0.63
    POSITIVE LOGITS
     glu
    1.37
     gluon
    1.26
     Glu
    1.13
    glu
    1.09
    Glu
    0.98
     glue
    0.85
     глю
    0.84
     胶
    0.77
    Glue
    0.76
     Glue
    0.75
    Activations Density 0.042%

    No Known Activations