© 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. 16103
    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
    -2.38
     both
    -1.70
    capai
    -1.62
     every
    -1.61
     all
    -1.60
     soyez
    -1.58
     or
    -1.55
     took
    -1.44
     from
    -1.42
     create
    -1.38
    POSITIVE LOGITS
     stalwart
    1.64
     wondrous
    1.54
     famed
    1.53
     AMAZING
    1.45
    g
    1.44
     idiotic
    1.38
     exceedingly
    1.37
    mainly
    1.37
     sumptuous
    1.36
    2
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.