© 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. 14575
    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
     after
    -1.53
     will
    -1.46
     first
    -1.34
     before
    -1.32
     in
    -1.24
     who
    -1.21
     five
    -1.21
     febrero
    -1.20
     which
    -1.20
     took
    -1.19
    POSITIVE LOGITS
     probablement
    1.27
     gigantic
    1.22
     Dinas
    1.20
    きち
    1.16
     Herbs
    1.14
     horrid
    1.13
     extremely
    1.13
     marvelous
    1.12
     insanely
    1.12
     mediocre
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.