© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 400
    Prev
    Next
    INDEX
    Explanations

    export or departure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     imported
    -0.99
    useEffect
    -0.93
     placement
    -0.89
     ingreso
    -0.85
     arrival
    -0.85
     influx
    -0.85
     Welcome
    -0.84
     langs
    -0.84
     entrada
    -0.83
     imports
    -0.82
    POSITIVE LOGITS
     export
    1.21
     departing
    1.07
     farewell
    1.02
     exporting
    1.01
     Export
    0.99
    export
    0.96
    Export
    0.95
     Abschied
    0.95
    EXPORT
    0.94
     EXPORT
    0.94
    Activations Density 0.147%

    No Known Activations