© 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. 95333
    Prev
    Next
    INDEX
    Explanations

    Michael Birch, Q, Now

    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
    سياسي
    -0.93
    dė
    -0.91
     stratég
    -0.84
     of
    -0.81
     acceptez
    -0.80
    🍿
    -0.80
    вши
    -0.78
     através
    -0.76
     sicuro
    -0.76
    férences
    -0.75
    POSITIVE LOGITS
    ienė
    1.05
    sió
    1.01
     diligen
    1.00
    Verte
    1.00
     inquiet
    0.96
     waiting
    0.95
     perce
    0.93
     wither
    0.93
     vklju
    0.89
     brevemente
    0.88
    Activations Density 0.002%

    No Known Activations