© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38536
    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
     its
    -1.96
     all
    -1.70
     their
    -1.68
     pö
    -1.57
     trö
    -1.56
     geef
    -1.54
     aparato
    -1.52
     it
    -1.50
     one
    -1.49
     münchen
    -1.48
    POSITIVE LOGITS
    0
    2.72
    なども
    1.65
    1
    1.63
    櫚
    1.56
    op
    1.50
    ut
    1.49
     exuber
    1.48
    ul
    1.48
    io
    1.47
     ingenu
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.