© 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. 12670
    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
    ㅇ
    -1.05
    пред
    -1.03
    To
    -1.02
     ),
    -1.02
    ymax
    -1.01
    ế
    -1.01
    ВД
    -1.00
    Stri
    -0.96
    ційний
    -0.96
     й
    -0.94
    POSITIVE LOGITS
     those
    1.36
     Auftritt
    1.32
     disparity
    1.04
    慣れて
    1.02
     Räume
    1.02
    莇
    1.02
     solches
    0.98
     zusätz
    0.97
    גרפיה
    0.95
     mevcut
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.