© 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. 9098
    Prev
    Next
    INDEX
    Explanations

    integrals and related math notation

    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
     you
    -1.51
     still
    -1.48
     TECHNOLOGIES
    -1.33
    ぎり
    -1.23
    utschen
    -1.22
    lekt
    -1.22
     \
    -1.19
     می‌
    -1.16
     toujours
    -1.13
     Mün
    -1.13
    POSITIVE LOGITS
     different
    1.70
     from
    1.62
     olika
    1.49
     various
    1.48
     різних
    1.45
     distintas
    1.41
     مختلف
    1.37
    不同的
    1.35
    ὅ
    1.31
     verschied
    1.30
    Activations Density 0.034%

    No Known Activations