© 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. 22-GEMMASCOPE-RES-131K
    7. 75238
    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
     their
    -2.63
     both
    -1.97
     at
    -1.94
     an
    -1.84
     before
    -1.82
     provide
    -1.76
     on
    -1.73
     any
    -1.72
     epitom
    -1.66
     without
    -1.63
    POSITIVE LOGITS
     Dinas
    1.60
    なども
    1.55
     gigantic
    1.52
     vua
    1.51
     wacky
    1.48
    despite
    1.47
    particularly
    1.46
     wonderfully
    1.45
     unbelievably
    1.45
     goofy
    1.44
    Activations Density 0.000%

    No Known Activations