© 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. 67504
    Prev
    Next
    INDEX
    Explanations

    UI element activation and events

    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
     chaque
    -1.04
    луй
    -1.02
     idyl
    -0.98
     topp
    -0.98
     órg
    -0.96
    RESUMEN
    -0.96
     contou
    -0.95
     hek
    -0.94
     tyn
    -0.94
     vielleicht
    -0.91
    POSITIVE LOGITS
     któ
    1.00
     ideje
    1.00
     laterales
    0.96
     wüns
    0.94
     vérit
    0.91
     wherefore
    0.90
     eight
    0.89
    citet
    0.88
     core
    0.88
     buvo
    0.87
    Activations Density 0.006%

    No Known Activations