© 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. 22-GEMMASCOPE-RES-131K
    7. 15153
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     fritas
    -1.19
     marron
    -1.15
     cherchés
    -1.09
     alicante
    -1.09
     amare
    -1.09
     cristi
    -1.06
     altres
    -1.05
    meester
    -1.04
     walang
    -1.03
     farmacia
    -1.03
    POSITIVE LOGITS
     that
    1.18
    (\
    1.01
    を目指す
    0.96
    IN
    0.96
    ’
    0.94
     and
    0.93
    %
    0.93
     Schuhe
    0.91
    らせ
    0.91
     idyllic
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.