© 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. 79792
    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
     for
    -1.77
     any
    -1.71
     because
    -1.66
     at
    -1.60
     only
    -1.59
     more
    -1.58
     without
    -1.55
     even
    -1.52
     after
    -1.49
     gives
    -1.49
    POSITIVE LOGITS
     insanely
    1.65
     astonishing
    1.60
     trám
    1.59
     fantastic
    1.59
     alluring
    1.58
     quintessential
    1.56
    GillaGilla
    1.55
     marvelous
    1.53
     horrible
    1.53
     wonderful
    1.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.