© 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. 66980
    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
     That
    -2.28
     those
    -2.08
     these
    -1.94
     their
    -1.90
     all
    -1.84
     every
    -1.83
     superbly
    -1.77
     terribly
    -1.77
     several
    -1.73
     ingenious
    -1.73
    POSITIVE LOGITS
     gena
    1.77
     frequentemente
    1.73
     beli
    1.73
     viste
    1.64
     beve
    1.63
     introd
    1.58
     suscit
    1.57
     provi
    1.55
     organis
    1.53
     Rè
    1.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.