© 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. 127559
    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
    Not in Any Lists

    No Comments

    Negative Logits
     kimono
    -1.06
     beſ
    -1.04
     Uranus
    -1.02
     myös
    -1.02
     圣诞
    -1.02
    似た
    -1.00
     Universo
    -0.98
    锈钢
    -0.95
    فاوت
    -0.94
     Suara
    -0.92
    POSITIVE LOGITS
    </b>
    0.96
     they
    0.96
    lasty
    0.95
     dinheiro
    0.91
    ometry
    0.91
     ra
    0.90
     case
    0.90
     De
    0.90
     a
    0.88
     O
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.