© 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. 75018
    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
    Adv
    -1.05
     trám
    -1.04
     attravers
    -1.02
    ВА
    -1.01
    觉得自己
    -0.97
     торже
    -0.96
     LAW
    -0.94
     casually
    -0.93
     culturali
    -0.91
     wszystkim
    -0.90
    POSITIVE LOGITS
     может
    1.04
     تمامی
    0.96
     können
    0.93
    
    0.93
    牡丹
    0.93
    
    0.89
    SCOTT
    0.88
     могут
    0.88
     —
    0.84
    Necesito
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.