© 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. 65944
    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
     órgãos
    -1.06
     può
    -1.05
     nawet
    -1.03
     shimmering
    -1.02
     ajoute
    -0.98
     Ради
    -0.97
     ralenti
    -0.96
     indivíduos
    -0.96
     membros
    -0.95
     ensayos
    -0.94
    POSITIVE LOGITS
     what
    1.06
     Extremely
    0.99
     With
    0.95
     both
    0.91
     one
    0.91
     Completely
    0.90
     could
    0.89
     an
    0.89
     FOR
    0.88
     innumerable
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.