© 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. 58262
    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
     måste
    -1.07
    менить
    -0.94
     behöver
    -0.93
    ⸫
    -0.92
     motion
    -0.90
     дела
    -0.90
     logra
    -0.89
    Than
    -0.88
    ทั้ง
    -0.88
     inútil
    -0.87
    POSITIVE LOGITS
    CROSSTALK
    1.02
     dorso
    0.95
    putnik
    0.93
    rogens
    0.93
     likely
    0.92
    )};
    0.92
    entikan
    0.90
     pren
    0.89
     közé
    0.86
    dafrika
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.