© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8972
    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
     árvores
    -0.99
    quences
    -0.96
    ));
    -0.92
     Spell
    -0.90
    Gates
    -0.90
     verão
    -0.89
    त
    -0.88
    Tar
    -0.86
     vinte
    -0.86
     recomenda
    -0.86
    POSITIVE LOGITS
     pidió
    1.05
     kepolisian
    1.02
     numerous
    0.97
     what
    0.96
     innumerable
    0.93
     atten
    0.93
     zobaczyć
    0.93
     Atas
    0.92
     audiences
    0.92
    μισ
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.