© 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. 22691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    يع
    -1.02
    科
    -0.98
    目前
    -0.97
    ["
    -0.96
    _
    -0.95
    ５
    -0.95
    𝐓
    -0.93
    Ди
    -0.92
    قام
    -0.92
    简约
    -0.92
    POSITIVE LOGITS
     étroite
    1.13
    etry
    1.05
     démocratique
    1.04
    TINGS
    0.98
     ajudar
    0.98
     veterinario
    0.97
     lidí
    0.96
     operativo
    0.94
     pengunjung
    0.92
     acolo
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.