© 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. 10-GEMMASCOPE-RES-131K
    7. 9995
    Prev
    Next
    INDEX
    Explanations

    special punctuation, symbols, or periods

    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_10/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
     what
    -1.56
    谩
    -1.43
    offrir
    -1.41
     how
    -1.40
     cuán
    -1.33
     contribuye
    -1.33
    与此同时
    -1.31
     predstav
    -1.30
     понимаю
    -1.30
     могла
    -1.30
    POSITIVE LOGITS
     your
    1.96
     alrededores
    1.57
     empfe
    1.52
    yecek
    1.50
     будет
    1.46
     hospitales
    1.45
     macetas
    1.45
     alojamientos
    1.45
     encuentran
    1.43
     आपको
    1.40
    Activations Density 0.072%

    No Known Activations