© 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. 128445
    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
     and
    -1.27
     ;
    -1.20
     what
    -1.16
     ''
    -1.16
     From
    -1.16
     who
    -1.14
     These
    -1.14
     images
    -1.14
     {}
    -1.13
     results
    -1.13
    POSITIVE LOGITS
     oignon
    1.58
     portefeuille
    1.55
     oreille
    1.51
     coussin
    1.42
     assise
    1.41
     carelessly
    1.39
     vingt
    1.39
     inextrica
    1.38
     aesthetically
    1.35
     miroir
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.