© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102617
    Prev
    Next
    INDEX
    Explanations

    describing abundance or specific terms like RichTextBox

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

    the word "rich" when it appears as part of compound terms or technical descriptions (like "glutamine-rich", "polysaccharide-rich", "RichTextBox").

    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
    on
    -3.05
     he
    -2.67
    螅
    -2.63
    翃
    -2.63
    枻
    -2.61
     “
    -2.59
    裢
    -2.53
     klassische
    -2.50
    ↵
    -2.44
    ༷
    -2.41
    POSITIVE LOGITS
    s
    3.94
     However
    3.03
     That
    3.03
    0
    2.77
     When
    2.70
    новь
    2.53
    
    2.52
    他的
    2.47
     giapp
    2.38
     而
    2.34
    Activations Density 0.009%

    No Known Activations