© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113722
    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
    ésie
    -1.16
     bize
    -1.09
    多元
    -0.96
    Twig
    -0.96
    матери
    -0.92
     león
    -0.92
     tatuaje
    -0.92
     caza
    -0.90
    ydı
    -0.88
     deportes
    -0.88
    POSITIVE LOGITS
     herbst
    1.09
    ()");
    1.09
    çou
    1.07
     Após
    1.05
    Initially
    1.05
     Should
    1.03
    niß
    0.99
     Когда
    0.98
     Даже
    0.96
     Eigh
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.