© 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. 10-GEMMASCOPE-RES-131K
    7. 58781
    Prev
    Next
    INDEX
    Explanations

    MMP and plasminogen activators

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

    This neuron identifies proteins and enzymes related to the plasminogen and metalloproteinase systems in scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting mentions of proteolytic enzymes, especially plasminogen activators and matrix metalloproteinases (MMPs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     gyermek
    -1.63
    
    -1.59
     palha
    -1.59
     renowned
    -1.55
     csalá
    -1.52
     acclaimed
    -1.52
     férfi
    -1.48
    ンドウ
    -1.48
     ergän
    -1.47
     folyam
    -1.47
    POSITIVE LOGITS
    </u>
    2.08
    ſſel
    1.78
    i
    1.75
    ]
    1.63
    </i>
    1.58
    to
    1.56
     was
    1.52
    tc
    1.50
    い
    1.47
    </h3>
    1.45
    Activations Density 0.099%

    No Known Activations