© 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. 6667
    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
     almacenar
    -1.01
     FACILITY
    -0.98
     Novgorod
    -0.98
    圌
    -0.96
     WILDLIFE
    -0.96
    ôme
    -0.96
     AGRIC
    -0.96
     paradiso
    -0.95
     LING
    -0.92
    脔
    -0.92
    POSITIVE LOGITS
     I
    1.02
     podí
    0.94
     Although
    0.94
     O
    0.91
     a
    0.88
    </h3>
    0.86
     персона
    0.84
     M
    0.84
     "
    0.84
     furnish
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.