© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74254
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating state or time

    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
     on
    -1.62
     new
    -1.38
    .(
    -1.38
    ņem
    -1.30
     during
    -1.30
     one
    -1.30
    ");
    -1.29
     by
    -1.29
    .”
    -1.29
    ">
    -1.28
    POSITIVE LOGITS
    kadang
    1.54
    нение
    1.38
    colates
    1.34
    particularly
    1.33
    cahontas
    1.30
    Cela
    1.30
    ticularly
    1.30
    Ⓢ
    1.29
     fiecare
    1.29
    баты
    1.29
    Activations Density 0.604%

    No Known Activations