© 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. 34-GEMMASCOPE-RES-131K
    7. 64165
    Prev
    Next
    INDEX
    Explanations

    collagen

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

    scientific terms related to collagen in research papers about tissue biology.

    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
     Molo
    -0.76
     kompetisi
    -0.75
     ブラック
    -0.73
     потра
    -0.68
     izle
    -0.67
    odeficiency
    -0.67
     vesicle
    -0.66
     monarch
    -0.66
     furnished
    -0.66
     Washer
    -0.66
    POSITIVE LOGITS
     collagen
    3.45
     Collagen
    2.67
    Col
    2.11
    col
    1.98
     COLL
    1.77
     collage
    1.69
    COLL
    1.67
     COL
    1.63
     col
    1.62
    COL
    1.56
    Activations Density 0.157%

    No Known Activations