© 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. 21708
    Prev
    Next
    INDEX
    Explanations

    names followed by de or family names

    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
    縢
    -1.52
     him
    -1.43
     nuvem
    -1.39
     deut
    -1.38
    ∙
    -1.37
    鈀
    -1.32
     gérer
    -1.30
     equipamentos
    -1.30
     laquelle
    -1.29
     testar
    -1.29
    POSITIVE LOGITS
     of
    2.20
     یا
    1.73
    힣
    1.45
     brugt
    1.38
     from
    1.32
     atau
    1.32
    красный
    1.31
     без
    1.29
    または
    1.28
     kecelakaan
    1.27
    Activations Density 0.056%

    No Known Activations