© 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. 34-GEMMASCOPE-RES-131K
    7. 59945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     it
    -1.02
     until
    -1.00
     without
    -0.93
     those
    -0.90
     for
    -0.84
     bądź
    -0.83
     вслед
    -0.83
     to
    -0.83
     countless
    -0.81
     after
    -0.81
    POSITIVE LOGITS
     continuare
    0.88
    懑
    0.88
     promesse
    0.87
     véhicules
    0.87
    avec
    0.81
    ffold
    0.80
     shou
    0.79
    fristig
    0.79
    Zna
    0.79
    спеди
    0.78
    Activations Density 0.000%

    No Known Activations