© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81549
    Prev
    Next
    INDEX
    Explanations

    protein helix and coil prediction

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

    protein structure terminology and descriptions, particularly terms related to alpha-helices, beta-sheets, and coiled-coil domains.

    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_34/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
    ඟ
    -0.78
    احت
    -0.78
    брю
    -0.75
    MPN
    -0.73
    ARIOS
    -0.72
     funkci
    -0.71
     swiftly
    -0.70
     audi
    -0.70
     kilometr
    -0.70
    وظ
    -0.70
    POSITIVE LOGITS
     Coil
    1.09
     helix
    1.06
    Coil
    1.02
    coil
    1.01
     coil
    0.97
     prediction
    0.94
     coils
    0.93
     helical
    0.92
    prediction
    0.87
    helix
    0.87
    Activations Density 0.047%

    No Known Activations