© 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. 128971
    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
     préalable
    -1.00
     店内
    -1.00
    Specifik
    -0.98
     there
    -0.94
    Previously
    -0.92
     cán
    -0.92
    *************/
    -0.91
    Istorija
    -0.91
     mezclar
    -0.91
    Several
    -0.90
    POSITIVE LOGITS
     more
    0.91
     optimizer
    0.81
    omenta
    0.80
     how
    0.80
    château
    0.78
     total
    0.78
     pensato
    0.78
     الطريق
    0.78
    änd
    0.77
    Southampton
    0.77
    Activations Density 0.001%

    No Known Activations