© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    names, sepsis, technical terms

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

    This neuron detects proper names of people, especially in formal documents and news articles.

    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
    蠊
    -2.72
    戩
    -2.63
    ?”
    -2.56
    鲣
    -2.41
    ～～～～
    -2.36
    桄
    -2.34
    
    -2.31
    ⟞
    -2.27
     coloridas
    -2.27
    摇了
    -2.27
    POSITIVE LOGITS
    </th>
    2.94
    </h1>
    2.52
    他已经
    2.50
    即便是
    2.48
    すすめ
    2.42
    while
    2.42
    .</
    2.38
    they
    2.36
    銲
    2.34
    she
    2.30
    Activations Density 0.013%

    No Known Activations