© 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. 43286
    Prev
    Next
    INDEX
    Explanations

    duplex ultrasound or villas

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

    The neuron detects the word "duplex" in technical and architectural contexts.

    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
    ௅
    -2.77
    瓛
    -2.61
    ↵
    -2.47
    に於
    -2.44
    彀
    -2.38
    栳
    -2.38
     vand
    -2.31
    crollView
    -2.27
     dessa
    -2.27
    肫
    -2.25
    POSITIVE LOGITS
    this
    3.20
    <bos>
    2.80
    \
    2.52
    All
    2.48
    s
    2.34
    ists
    2.31
     cheesy
    2.28
    あります
    2.28
    It
    2.27
    時間も
    2.25
    Activations Density 0.006%

    No Known Activations