© 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. 34-GEMMASCOPE-RES-131K
    4. 73355
    Prev
    Next
    INDEX
    Explanations

    angiogenesis, angiogenic, angiopathy, angiomyolipoma

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

    The neuron activates for the word "angio" in medical contexts like "angiogenesis" and other angio-related terms.

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

    The neuron detects terms containing the “angio-” prefix (e.g. angiogenesis, angiogenic, angiopathy).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     khả
    -0.89
    ardige
    -0.87
     Stupid
    -0.86
     Gefühle
    -0.81
     spate
    -0.80
    comprar
    -0.80
     Unterschied
    -0.79
    謔
    -0.78
     profondo
    -0.76
    seamnă
    -0.75
    POSITIVE LOGITS
     Ang
    1.03
    Ang
    1.03
     первую
    0.88
    appropri
    0.88
    /**
    0.88
     ang
    0.87
    𝗵
    0.84
     Ан
    0.84
     Angst
    0.83
     át
    0.82
    Activations Density 0.039%

    No Known Activations