© 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. 79559
    Prev
    Next
    INDEX
    Explanations

    geographic locations and descriptions

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

    The neuron activates on numbers and measurement-related tokens (quantities, units, and numeric data) in scientific contexts.

    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
    participant
    -0.90
    APY
    -0.86
     Library
    -0.84
     PACK
    -0.83
    raf
    -0.82
     irrig
    -0.81
    flowers
    -0.80
    Kde
    -0.80
     Oliven
    -0.80
    Výhody
    -0.80
    POSITIVE LOGITS
     dorm
    0.95
    പ്
    0.93
     mowing
    0.83
     Mez
    0.82
     cereal
    0.80
    睡
    0.79
    以上的
    0.78
     Adonis
    0.78
     Scots
    0.77
     decked
    0.77
    Activations Density 0.052%

    No Known Activations