© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85963
    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
    ských
    -0.96
     Recently
    -0.92
    +```
    -0.90
    </em>
    -0.88
     recently
    -0.83
     fino
    -0.82
     %
    -0.82
     specialised
    -0.81
     Ihren
    -0.81
    Ваш
    -0.81
    POSITIVE LOGITS
    してきました
    0.99
    涠
    0.93
     asl
    0.90
    或許
    0.90
     الصغيرة
    0.90
     canaux
    0.88
    tiful
    0.88
     yy
    0.88
     duquel
    0.88
     anys
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.