© 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. 65098
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with hyphens

    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
    ſſen
    -1.95
     épo
    -1.70
     “…
    -1.64
     fêtes
    -1.63
    </b>
    -1.60
     “
    -1.56
    ’)
    -1.54
     pà
    -1.52
    ogues
    -1.52
     maroc
    -1.52
    POSITIVE LOGITS
     kaplama
    1.62
     ИН
    1.59
     lisäksi
    1.52
     estekak
    1.52
     объясня
    1.52
     аккура
    1.48
     置物
    1.48
     sokak
    1.45
    ום
    1.43
     çoğu
    1.43
    Activations Density 0.113%

    No Known Activations