© 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. 8071
    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
     cuadrado
    -1.27
    ではなく
    -1.27
     또는
    -1.20
    または
    -1.18
     począ
    -1.15
     یا
    -1.12
     janu
    -1.12
    だけではなく
    -1.11
    или
    -1.11
     eller
    -1.11
    POSITIVE LOGITS
     because
    1.38
     by
    1.32
     one
    1.29
    acate
    1.24
     This
    1.18
     as
    1.18
    ámica
    1.17
    桔
    1.17
    because
    1.13
     What
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.