© 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. 47580
    Prev
    Next
    INDEX
    Explanations

    let followed by variable or phrase

    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
    鹇
    -1.63
    圌
    -1.62
     Répondre
    -1.52
    lao
    -1.49
    
    -1.48
     disposto
    -1.48
     žem
    -1.48
    urization
    -1.48
     Milliarden
    -1.44
     يص
    -1.44
    POSITIVE LOGITS
     入っ
    1.47
    ？（
    1.38
    ֺ
    1.36
     be
    1.34
     nuevos
    1.34
    ятся
    1.30
    ！(
    1.30
    我对
    1.30
    ？！
    1.23
     vhodné
    1.23
    Activations Density 0.028%

    No Known Activations