© 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. 90759
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities

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

    The neuron activates on quantitative descriptor words in scientific contexts—that is, terms used to introduce or characterize measured values or results.

    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
    trials
    -1.06
    units
    -0.93
    Projects
    -0.90
    projects
    -0.89
    plugins
    -0.89
     pranks
    -0.88
    documents
    -0.87
    islands
    -0.87
    events
    -0.86
    clusters
    -0.84
    POSITIVE LOGITS
     sizes
    2.38
     values
    2.30
     prices
    2.16
     widths
    2.16
     distances
    1.98
     speeds
    1.95
     heights
    1.87
     temperatures
    1.87
     lengths
    1.87
     thicknesses
    1.85
    Activations Density 0.427%

    No Known Activations