© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129509
    Prev
    Next
    INDEX
    Explanations

    aged people

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

    The neuron detects numeric age expressions (e.g. “17-year-old,” “57-year-old”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.67
     by
    -1.95
     When
    -1.78
     In
    -1.73
     in
    -1.70
     except
    -1.70
     different
    -1.67
     for
    -1.61
     if
    -1.59
     come
    -1.59
    POSITIVE LOGITS
     bañera
    2.08
     calefacción
    1.94
     agujeros
    1.86
     adhesivo
    1.84
     iluminación
    1.82
     ventilación
    1.82
     oxígeno
    1.80
    Nhưng
    1.77
     lavadora
    1.77
     restauración
    1.74
    Activations Density 0.058%

    No Known Activations