© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130122
    Prev
    Next
    INDEX
    Explanations

    Muir, mee, HDL

    np_acts-logits-general · gemini-2.5-flash-lite

    Chinese or East Asian names and terminology, especially the syllable "hui" and other Chinese surname components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    1
    -3.72
    3
    -3.02
    ↵
    -3.02
    没什么
    -2.77
    上記の
    -2.75
    5
    -2.75
    尨
    -2.72
    8
    -2.69
    翃
    -2.59
     earnest
    -2.58
    POSITIVE LOGITS
    We
    3.36
    {
    3.33
    🌟
    3.11
     車場
    3.03
     medica
    3.00
     itſelf
    2.94
    🌸
    2.94
    ❤
    2.92
     内衣
    2.88
    💕
    2.72
    Activations Density 0.002%

    No Known Activations