© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42932
    Prev
    Next
    INDEX
    Explanations

    Seattle and Washington locations

    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
    at
    -1.51
    -
    -1.49
    发行
    -1.45
     -
    -1.35
     Серге
    -1.27
    他自己
    -1.27
     moeten
    -1.24
     ‘
    -1.22
     festen
    -1.22
     naturelles
    -1.21
    POSITIVE LOGITS
    Bibitem
    1.49
     titolata
    1.48
    ikyuu
    1.42
     únicamente
    1.39
     wien
    1.38
     Genève
    1.38
     Göteborg
    1.37
     about
    1.36
    wwww
    1.34
    鹛
    1.34
    Activations Density 0.019%

    No Known Activations