© 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. 34-GEMMASCOPE-RES-131K
    7. 111091
    Prev
    Next
    INDEX
    Explanations

    service, serving, serve

    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_34/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
    ್ದ
    -0.85
    canakan
    -0.78
     طرف
    -0.77
    íslu
    -0.77
     trương
    -0.75
    דת
    -0.74
    寓意
    -0.74
    远程
    -0.74
     ヴィトン
    -0.73
     Halb
    -0.73
    POSITIVE LOGITS
     service
    3.13
     serving
    2.95
     serve
    2.73
     servant
    2.66
     servir
    2.45
    服务
    2.36
     servicio
    2.31
     Serving
    2.30
    serving
    2.28
    serve
    2.27
    Activations Density 0.020%

    No Known Activations