© 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. 101241
    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
    Willie
    -1.08
    glise
    -1.08
     utilisée
    -1.05
    菀
    -1.05
     Pflege
    -1.02
    WTF
    -0.94
     retribution
    -0.94
    ïe
    -0.92
    Jefferson
    -0.91
    cipated
    -0.90
    POSITIVE LOGITS
    s
    1.30
    ويات
    1.03
    ophyll
    0.99
    cznych
    0.98
     pollici
    0.96
     they
    0.95
    ㅕ
    0.94
    .\\
    0.93
     that
    0.93
     balenciaga
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.