© 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. 44243
    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
    .
    -2.44
    ’
    -1.66
     The
    -1.63
    往往
    -1.62
    (
    -1.60
     wasn
    -1.56
     aumenta
    -1.55
    _
    -1.52
    &
    -1.51
    la
    -1.48
    POSITIVE LOGITS
    lichung
    1.60
    تفسير
    1.49
     négociations
    1.48
     metales
    1.47
    Besitos
    1.47
    ános
    1.47
     wspania
    1.45
     deur
    1.45
    welijk
    1.43
     soldadura
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.