© 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. 119918
    Prev
    Next
    INDEX
    Explanations

    communication origin

    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
    și
    -1.34
     septembre
    -1.30
    ÇA
    -1.28
    CELONA
    -1.25
     to
    -1.24
    gå
    -1.22
    September
    -1.19
    ølge
    -1.18
     wolle
    -1.17
    儉
    -1.17
    POSITIVE LOGITS
     recientemente
    1.71
     from
    1.50
    Traduction
    1.48
     by
    1.48
     dotyczące
    1.45
     yapımı
    1.43
    很赞
    1.38
    時点
    1.37
     originalmente
    1.35
     thoáng
    1.35
    Activations Density 0.045%

    No Known Activations