© 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. 66028
    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
     this
    -1.65
     which
    -1.52
     have
    -1.48
     it
    -1.47
     for
    -1.43
     before
    -1.27
     if
    -1.27
     with
    -1.23
     some
    -1.22
     what
    -1.22
    POSITIVE LOGITS
    u
    1.55
    苙
    1.41
    io
    1.33
     famed
    1.32
    is
    1.29
    k
    1.28
    q
    1.27
    ar
    1.27
    j
    1.27
    os
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.