© 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. 10-GEMMASCOPE-RES-131K
    4. 104430
    Prev
    Next
    INDEX
    Explanations

    extracellular matrix and collagen

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

    The neuron identifies protein and matrix components in scientific texts about extracellular matrices, particularly recognizing terms like "collagen," "laminin," "proteoglycan," and related biochemical structures.

    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
    ologico
    -1.55
    us
    -1.51
     экономических
    -1.39
    價格
    -1.35
    last
    -1.29
    そういえば
    -1.28
    一只
    -1.28
     造型
    -1.27
     bact
    -1.25
     you
    -1.24
    POSITIVE LOGITS
     both
    1.44
     prácticamente
    1.42
    </strong>
    1.38
     February
    1.37
     hardly
    1.36
     especially
    1.34
     barely
    1.33
    ouflage
    1.31
     particularly
    1.30
     大人
    1.30
    Activations Density 0.215%

    No Known Activations