© 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. 10-GEMMASCOPE-RES-131K
    7. 39284
    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
    züglich
    -0.99
    鍮
    -0.98
     spannend
    -0.94
    loroethene
    -0.93
    ות
    -0.92
     Christus
    -0.91
    lamabad
    -0.91
    邹
    -0.91
     Emulator
    -0.91
     Cradle
    -0.91
    POSITIVE LOGITS
     Many
    1.02
     By
    1.00
    訛
    0.98
     jedoch
    0.91
     which
    0.90
    本店
    0.88
     wprowad
    0.87
     Before
    0.87
    弐
    0.85
     During
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.