© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118755
    Prev
    Next
    INDEX
    Explanations

    metropolitan statistical areas

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

    The neuron is detecting quantitative/statistical tokens—numbers and numeric data (e.g. population figures, years, area codes, and related statistical labels).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     predictors
    -0.79
    Encontra
    -0.78
    可以通过
    -0.77
     коле
    -0.75
    Needle
    -0.75
    μένο
    -0.74
    Epoxy
    -0.74
    essura
    -0.73
     continents
    -0.73
     Colleagues
    -0.72
    POSITIVE LOGITS
     metro
    1.92
     metropolitan
    1.88
     Greater
    1.73
     Metro
    1.62
    Greater
    1.61
     Metropolitan
    1.52
    Metro
    1.51
    metro
    1.49
     greater
    1.40
     area
    1.29
    Activations Density 0.087%

    No Known Activations