© 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. 15696
    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
    They
    -1.05
    thentication
    -0.94
    quando
    -0.92
    Their
    -0.91
     όμως
    -0.90
    0
    -0.86
    unless
    -0.86
     unless
    -0.86
     чтобы
    -0.84
    　　
    -0.82
    POSITIVE LOGITS
     būt
    0.97
     Vordergrund
    0.95
     procesu
    0.94
    gunas
    0.93
    andten
    0.91
    🌿
    0.91
     Forgotten
    0.90
    wikidata
    0.90
    ianza
    0.89
     bonitas
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.