© 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. 19895
    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
     入っ
    -1.19
     is
    -1.18
     rápidos
    -1.17
     incorpora
    -1.16
     
    -1.16
    跟你
    -1.14
    是你
    -1.14
     evidencia
    -1.13
     emphas
    -1.13
    塀
    -1.13
    POSITIVE LOGITS
     These
    1.34
    خان
    1.30
     problemy
    1.27
     problemu
    1.24
    Merkmale
    1.23
    iredo
    1.21
    بیشتر
    1.20
    Setiap
    1.20
     gomez
    1.20
     lebte
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.