© 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. 74442
    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
     and
    -0.99
     Học
    -0.88
     veľmi
    -0.88
     origins
    -0.87
     цели
    -0.86
    ／
    -0.86
     schmerz
    -0.86
     börja
    -0.85
    ostro
    -0.85
    稅
    -0.84
    POSITIVE LOGITS
     sade
    1.05
    Arrangement
    1.03
     beig
    1.01
     centru
    0.99
     LIABLE
    0.98
     insan
    0.96
    蹓
    0.95
    独自の
    0.94
    Alu
    0.93
    вић
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.