© 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. 114108
    Prev
    Next
    INDEX
    Explanations

    born or age

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

    The neuron activates on numeric tokens—years, ages, dates, quantities, and other numbers.

    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
     originalen
    -1.81
     komplette
    -1.79
     redaktion
    -1.45
    
    -1.45
    侂
    -1.43
    噓
    -1.42
     verdadeira
    -1.41
    ⚌
    -1.40
     konkrete
    -1.38
     acessórios
    -1.36
    POSITIVE LOGITS
    .
    1.81
    2
    1.54
    3
    1.50
    V
    1.46
     любить
    1.44
     Venise
    1.44
    4
    1.42
    ’
    1.39
     after
    1.36
     Unlike
    1.36
    Activations Density 0.012%

    No Known Activations