© 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. 123741
    Prev
    Next
    INDEX
    Explanations

    XML configuration and code elements

    np_acts-logits-general · gemini-2.5-flash-lite

    XML configuration and build files, particularly those used in software development projects (like Xcode schemes, Maven dependencies, and MSBuild configurations).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     or
    -1.48
     memahami
    -1.34
    '
    -1.26
     думать
    -1.24
     a
    -1.20
     Around
    -1.20
     According
    -1.20
     dormir
    -1.19
     beslu
    -1.19
     parfüm
    -1.17
    POSITIVE LOGITS
    笵
    1.45
     up
    1.39
     situazioni
    1.34
    縢
    1.32
    ≔
    1.27
    Recursos
    1.24
    ียน
    1.24
    lerden
    1.24
     that
    1.23
    want
    1.23
    Activations Density 0.018%

    No Known Activations