© 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. 119049
    Prev
    Next
    INDEX
    Explanations

    `&` and `"` entities

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

    HTML entity codes, particularly the ampersand entity "&" in encoded text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    妧
    -1.65
    蒌
    -1.63
     mancher
    -1.63
     juste
    -1.57
    蓠
    -1.56
     lumber
    -1.52
    蚰
    -1.51
    INGE
    -1.48
     ancienne
    -1.48
    脔
    -1.48
    POSITIVE LOGITS
    These
    1.95
    when
    1.89
     when
    1.87
     that
    1.83
     could
    1.79
     cannot
    1.77
     and
    1.69
     These
    1.68
    岘
    1.64
     for
    1.63
    Activations Density 0.021%

    No Known Activations