© 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. 119656
    Prev
    Next
    INDEX
    Explanations

    cy in cygwin, cyano, cytidine, cygnus, cytoplasmic

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

    "cy" letter combinations in various technical contexts (chemical compounds, computer code, and domain names).

    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
    其妙
    -2.97
    CHREIB
    -2.92
     名前
    -2.72
    鋮
    -2.72
     メニュー
    -2.69
    蹋
    -2.59
     groter
    -2.55
    pecabe
    -2.52
    齜
    -2.50
     вона
    -2.48
    POSITIVE LOGITS
    h
    3.81
    e
    3.55
    i
    3.44
    cy
    3.33
    a
    3.28
     {
    3.25
     `
    3.16
    )
    2.98
    蟥
    2.95
    2.88
    Activations Density 0.009%

    No Known Activations