© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43165
    Prev
    Next
    INDEX
    Explanations

    VEGF gene receptors

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

    This neuron activates for proper nouns, particularly "Somali" and "VEGF" (Vascular Endothelial Growth Factor), as well as some person names.

    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
    a
    -2.77
    ﻂ
    -2.53
    🪆
    -2.44
    ԋ
    -2.39
    ጐ
    -2.38
    廰
    -2.38
     लेकिन
    -2.36
    плення
    -2.31
    AdvEx
    -2.30
    屙
    -2.30
    POSITIVE LOGITS
    逦
    2.88
    because
    2.75
    on
    2.75
    just
    2.61
     
    2.59
     Relatively
    2.50
    as
    2.50
    what
    2.48
    作為
    2.48
    .”
    2.47
    Activations Density 0.005%

    No Known Activations