© 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. 67815
    Prev
    Next
    INDEX
    Explanations

    today and modern

    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
     ancien
    -1.11
    previously
    -1.10
    romeda
    -1.09
    formerly
    -1.09
    tocks
    -1.07
    berichte
    -1.07
    .*,
    -1.07
    もともと
    -1.07
    heds
    -1.05
    moiselle
    -1.02
    POSITIVE LOGITS
     today
    3.48
    Today
    2.25
     current
    2.25
     modern
    2.17
     aujourd
    2.09
     امروز
    2.09
     σήμερα
    2.06
     heutigen
    2.05
    現在
    2.02
    today
    2.02
    Activations Density 0.044%

    No Known Activations