© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102709
    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
     istor
    -0.99
     ours
    -0.98
    ormais
    -0.96
     crammed
    -0.96
    ningarna
    -0.94
    uens
    -0.93
    因为它
    -0.91
    ITCHEN
    -0.91
     atún
    -0.90
    监控
    -0.89
    POSITIVE LOGITS
    dzić
    1.00
    datable
    0.96
    medal
    0.94
     "...
    0.93
    gradable
    0.93
     podrá
    0.93
    
    0.90
    นวน
    0.88
    либо
    0.88
     iii
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.