© 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. 119667
    Prev
    Next
    INDEX
    Explanations

    prepositions introducing context

    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
     first
    -1.52
    אין
    -1.34
    ဴ
    -1.32
    aların
    -1.27
     pantaloni
    -1.27
    AllAfrica
    -1.23
    Ruju
    -1.22
    Dipl
    -1.21
     beneficial
    -1.19
    дил
    -1.19
    POSITIVE LOGITS
    岨
    1.59
    ⎔
    1.55
     tijd
    1.34
    several
    1.34
    
    1.34
    either
    1.30
    𝑀
    1.29
    Ő
    1.27
    garder
    1.26
     my
    1.24
    Activations Density 0.104%

    No Known Activations