© 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. 34-GEMMASCOPE-RES-131K
    7. 103430
    Prev
    Next
    INDEX
    Explanations

    collagen and its components

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

    scientific terminology related to collagen and other proteins in biological research.

    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
    кладки
    -0.82
     multiplied
    -0.79
     multiplying
    -0.78
    เร็ว
    -0.78
     ایران
    -0.75
    RQ
    -0.74
    出会
    -0.73
    뇌
    -0.73
    不動
    -0.73
    /*++
    -0.72
    POSITIVE LOGITS
     tropo
    0.98
     telo
    0.87
     Eyre
    0.83
     triple
    0.80
    Skin
    0.80
    甸
    0.79
    bloom
    0.79
    TGF
    0.77
     glycine
    0.77
    triple
    0.76
    Activations Density 0.114%

    No Known Activations