© 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. 25294
    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
     all
    -1.64
     if
    -1.63
     one
    -1.45
     what
    -1.35
     only
    -1.35
     arguably
    -1.28
     just
    -1.27
     had
    -1.27
     Creating
    -1.26
     having
    -1.25
    POSITIVE LOGITS
     AMAZING
    1.52
     marvelous
    1.34
    鴴
    1.32
     soooo
    1.28
    
    1.27
    푉
    1.27
     captivating
    1.26
    aimeJ
    1.26
     THROUGH
    1.24
     opulent
    1.24
    Activations Density 0.000%

    No Known Activations