© 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. 10-GEMMASCOPE-RES-131K
    7. 73773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     these
    -1.95
     those
    -1.49
     two
    -1.39
     there
    -1.34
     necessary
    -1.32
     be
    -1.30
     .
    -1.27
     easier
    -1.27
     this
    -1.27
     valuable
    -1.25
    POSITIVE LOGITS
     anys
    1.49
    бол
    1.39
     anderson
    1.34
     biling
    1.32
     compositeur
    1.31
     absolut
    1.27
     sufic
    1.27
    は
    1.25
     DEFIN
    1.25
    |"
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.