© 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. 66002
    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
     it
    -1.28
     or
    -1.28
     and
    -1.19
     most
    -1.14
     their
    -1.13
    zku
    -1.12
     before
    -1.12
     Although
    -1.11
     kotor
    -1.09
     first
    -1.09
    POSITIVE LOGITS
     включая
    1.40
    などが
    1.40
    including
    1.38
     quintessential
    1.33
     incluyendo
    1.30
     namely
    1.30
     hefty
    1.27
    が
    1.27
     incluindo
    1.24
     goofy
    1.23
    Activations Density 0.000%

    No Known Activations