© 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. 104512
    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
     pantalón
    -1.29
    梆
    -1.28
     esfuerzos
    -1.27
     geringe
    -1.26
     genaue
    -1.23
    gelijke
    -1.20
     begren
    -1.19
     restauración
    -1.19
    itieren
    -1.16
    almente
    -1.16
    POSITIVE LOGITS
     our
    1.55
    ".
    1.20
    ",
    1.14
    >
    1.12
     among
    1.11
    ),
    1.10
    するので
    1.05
     if
    1.02
     before
    1.02
     to
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.