© 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. 127304
    Prev
    Next
    INDEX
    Explanations

    endings, deaths, or specific roles

    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
    bbles
    -1.48
     行
    -1.45
     '"
    -1.37
     perché
    -1.34
    現在
    -1.34
    either
    -1.33
     現在
    -1.33
    WriteLiteral
    -1.33
     約
    -1.32
    other
    -1.31
    POSITIVE LOGITS
     all
    1.38
     doba
    1.38
    اقتصاد
    1.36
     pulseira
    1.35
    性は
    1.32
    imageList
    1.32
     stets
    1.31
    электро
    1.30
    立った
    1.27
     FÜR
    1.27
    Activations Density 0.271%

    No Known Activations