© 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. 113206
    Prev
    Next
    INDEX
    Explanations

    growth factor

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

    The neuron identifies and activates for the phrase "growth factor," particularly in biomedical contexts related to vascular endothelial growth factor (VEGF) 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_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
     anadolu
    -1.84
    dersfield
    -1.65
    ᠂
    -1.62
    
    -1.61
     '"
    -1.61
     bloquer
    -1.61
     kapak
    -1.59
     diki
    -1.54
    something
    -1.54
    就能
    -1.53
    POSITIVE LOGITS
     these
    1.86
     on
    1.81
     by
    1.66
     many
    1.53
     all
    1.50
     Even
    1.50
     Before
    1.47
     before
    1.41
     this
    1.36
     without
    1.36
    Activations Density 0.148%

    No Known Activations