© 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. 73658
    Prev
    Next
    INDEX
    Explanations

    about [topic]

    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
    է
    -1.02
     it
    -1.01
    ↵↵
    -0.98
     similarly
    -0.97
    قامت
    -0.95
     its
    -0.94
     those
    -0.93
    なりに
    -0.90
     mittlerweile
    -0.90
    同様
    -0.88
    POSITIVE LOGITS
     chaque
    1.06
    ейчас
    1.02
     annuel
    0.99
    ǚ
    0.96
    atee
    0.95
     montagne
    0.95
    жк
    0.94
     estadounid
    0.93
     mondi
    0.92
    щик
    0.90
    Activations Density 0.001%

    No Known Activations