© 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. 106310
    Prev
    Next
    INDEX
    Explanations

    wearable wrist devices

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

    The neuron selectively activates on numerical tokens (digits, model numbers, percentages, and other number sequences).

    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
     電動
    -0.91
    ետ
    -0.88
    רונות
    -0.88
    clable
    -0.88
     Laptops
    -0.87
     ноутбу
    -0.86
     laptops
    -0.84
    dvd
    -0.84
     signage
    -0.84
    DVD
    -0.83
    POSITIVE LOGITS
     Wear
    1.62
     wearer
    1.62
     wearable
    1.53
     wrist
    1.51
     wear
    1.39
     fitness
    1.38
    Wear
    1.35
     wearing
    1.34
    wear
    1.27
     smartwatch
    1.26
    Activations Density 0.031%

    No Known Activations