© 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. 70845
    Prev
    Next
    INDEX
    Explanations

    Henderson and Dawson

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

    proper last names, particularly "Henderson" and names ending with "son".

    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
    栊
    -3.05
    梣
    -2.95
    釙
    -2.94
    呖
    -2.84
    垍
    -2.80
    軚
    -2.80
    栳
    -2.72
     icône
    -2.52
    bảng
    -2.48
     eccellente
    -2.47
    POSITIVE LOGITS
    ↵
    4.06
    </h2>
    2.95
    ated
    2.70
     Then
    2.56
    </em>
    2.55
     Our
    2.44
     For
    2.36
     
    2.34
    趼
    2.14
     наши
    2.09
    Activations Density 0.006%

    No Known Activations