© 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. 128438
    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
     have
    -1.23
     two
    -1.16
     when
    -0.98
     more
    -0.97
     where
    -0.96
     all
    -0.96
     really
    -0.96
     versión
    -0.96
     just
    -0.94
     want
    -0.93
    POSITIVE LOGITS
     millennia
    1.01
    铄
    0.99
    的东西
    0.99
     fournit
    0.98
    ровке
    0.97
     plancher
    0.97
    PDOException
    0.94
     osoba
    0.93
    ﻱ
    0.92
    谖
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.