© 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. 26403
    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
    -1.88
     even
    -1.60
     any
    -1.48
     all
    -1.42
     truly
    -1.41
     more
    -1.39
     several
    -1.36
     by
    -1.36
     having
    -1.34
     what
    -1.34
    POSITIVE LOGITS
     momentous
    1.41
     astounding
    1.38
     😁
    1.28
     horrifying
    1.28
     marvelous
    1.27
     luscious
    1.26
     gigantic
    1.25
     ざ
    1.24
     wondrous
    1.24
     astonishing
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.