© 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. 39273
    Prev
    Next
    INDEX
    Explanations

    disperse

    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
    霎
    -2.78
    几个月
    -2.56
     bliss
    -2.53
     they
    -2.53
    泐
    -2.52
    ができます
    -2.47
    を果た
    -2.42
    怍
    -2.39
     acidente
    -2.34
    
    -2.34
    POSITIVE LOGITS
     детьми
    2.47
    ität
    2.33
    isierte
    2.31
    Alemania
    2.20
    不断
    2.16
    Отзывы
    2.05
    ientos
    2.03
    España
    2.02
    ierung
    2.00
    ↑↑↑</
    1.99
    Activations Density 0.006%

    No Known Activations