© 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. 22-GEMMASCOPE-RES-131K
    7. 26019
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     
    -1.09
    Hvem
    -1.02
     a
    -1.02
    )
    -0.99
    ^{\
    -0.98
     captivated
    -0.97
    Britain
    -0.96
     camas
    -0.95
    BU
    -0.94
    holdet
    -0.93
    POSITIVE LOGITS
     latter
    1.05
    
    1.00
     الأخيرة
    0.96
    ꇴ
    0.94
    ذة
    0.94
    🥷
    0.90
     افزار
    0.90
     получают
    0.88
     helyez
    0.88
     všetky
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.