© 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. 19148
    Prev
    Next
    INDEX
    Explanations

    maximizing outcomes

    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
    {
    -2.53
    .''
    -2.53
    (
    -2.34
    ?''
    -2.28
    )--
    -2.27
    
    -2.23
     exercí
    -2.20
     judíos
    -2.20
     This
    -2.16
    的重要
    -2.16
    POSITIVE LOGITS
    呖
    3.09
    战场
    2.45
    〜。
    2.30
    蹀
    2.22
    Chances
    2.20
    ,’
    2.17
    Ꮠ
    2.14
     可爱
    2.08
    Grafik
    2.06
    絰
    2.06
    Activations Density 0.006%

    No Known Activations