© 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. 41435
    Prev
    Next
    INDEX
    Explanations

    slay and slain

    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
    d
    -2.91
     και
    -2.39
     и
    -2.34
    里有
    -2.30
    ↑↑↑</
    -2.25
    hörigen
    -2.23
     tries
    -2.20
    ons
    -2.13
     techniczne
    -2.13
     implies
    -2.11
    POSITIVE LOGITS
    <
    2.78
    𝐒
    2.55
     Quando
    2.47
     wonderfully
    2.30
     chirurg
    2.13
     presentaron
    2.11
     she
    2.05
    𓋼
    2.05
     marvelous
    2.05
    毉
    2.00
    Activations Density 0.003%

    No Known Activations