© 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. 129517
    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
    droj
    -1.15
    Numerous
    -1.13
    LIOT
    -1.13
    ּוֹ
    -1.05
    较为
    -1.05
    März
    -1.04
    зок
    -1.04
    Eigenschaften
    -1.02
    Those
    -1.02
     profesora
    -1.01
    POSITIVE LOGITS
     terrific
    1.25
     fantastic
    1.14
     amazing
    1.09
     hugely
    1.08
     tratamento
    1.06
     captivating
    1.05
     amazingly
    1.05
     incredibly
    1.05
     focuses
    1.05
     hasta
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.