© 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. 10-GEMMASCOPE-RES-131K
    7. 6854
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron fires on sequences of numeric characters (multi‐digit numbers such as phone numbers, dates, ZIP/postal codes, etc.).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     there
    -1.99
    there
    -1.45
    อื่น
    -1.44
     ativos
    -1.34
     a
    -1.34
     otros
    -1.30
     that
    -1.26
     nacidos
    -1.23
     alemanes
    -1.23
    hodné
    -1.23
    POSITIVE LOGITS
     to
    1.37
     todav
    1.33
    1
    1.28
    матика
    1.28
    екси
    1.27
    strokeWeight
    1.23
    2
    1.23
    に対し
    1.23
     kjer
    1.20
    0
    1.20
    Activations Density 0.041%

    No Known Activations