© 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. 102414
    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
     proved
    -1.02
                        
    -0.93
     this
    -0.92
     more
    -0.91
     gabri
    -0.91
     saul
    -0.88
           
    -0.86
     firmly
    -0.86
     always
    -0.85
     showed
    -0.85
    POSITIVE LOGITS
     område
    1.22
     комната
    1.21
     çocu
    1.16
    tholes
    1.12
     votación
    1.10
     Unterschiede
    1.08
     recommandons
    1.04
     nový
    1.01
     schlechter
    1.00
     nowoczes
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.