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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1225
    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
    </h3>
    -1.74
    </strong>
    -1.46
     für
    -1.28
    ";
    -1.26
    !”
    -1.26
     Publikum
    -1.21
     untuk
    -1.19
     glue
    -1.16
    ,“
    -1.16
    </th>
    -1.15
    POSITIVE LOGITS
    笵
    1.34
     Vrbo
    1.20
     mépris
    1.17
    の概要
    1.17
    幸好
    1.17
     ダブル
    1.16
     Redacción
    1.15
    了出去
    1.14
    コチラ
    1.13
    我也是
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.