© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86022
    Prev
    Next
    INDEX
    Explanations

    urogenital, Haarlem

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

    characters or letter sequences specific to non-English languages, especially from Germanic and Slavic language families.

    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
     weißem
    -2.20
    <bos>
    -2.19
    ор
    -1.97
    日曜
    -1.95
     submissive
    -1.94
    charest
    -1.89
    さんも
    -1.86
    ників
    -1.86
     豐
    -1.85
     będziemy
    -1.79
    POSITIVE LOGITS
    䜣
    2.55
    </h1>
    2.36
    鰱
    2.25
     "
    
    2.19
     own
    2.19
    ICOLON
    2.16
    this
    2.14
    訁
    2.14
    蛱
    2.11
    
    2.11
    Activations Density 0.000%

    No Known Activations