© 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. 85056
    Prev
    Next
    INDEX
    Explanations

    greek letters

    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
    躥
    -2.23
    before
    -1.96
    袮
    -1.94
     aktualisiert
    -1.91
    Rather
    -1.90
    …’
    -1.90
    灕
    -1.87
     angegeben
    -1.84
     schönes
    -1.82
    不是
    -1.79
    POSITIVE LOGITS
     \
    2.13
     &
    1.88
     ''
    1.84
    e
    1.80
    "
    1.78
    々の
    1.77
     Vierge
    1.75
     parfü
    1.73
     réalisateur
    1.71
     of
    1.70
    Activations Density 0.127%

    No Known Activations