© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19423
    Prev
    Next
    INDEX
    Explanations

    luminal structures

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

    The neuron detects references to anatomical lumens or channels within the body.

    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
     ſou
    -3.38
    
    -3.25
    凊
    -2.70
    摀
    -2.66
     dreary
    -2.56
    餿
    -2.53
    ⃠
    -2.50
     unending
    -2.48
     mesmerizing
    -2.45
     captivating
    -2.44
    POSITIVE LOGITS
     and
    2.16
    ⦊
    2.03
     OGSÅ
    2.03
     longstanding
    2.02
    <em>
    1.96
    𖥧
    1.96
     enhanced
    1.88
     extraordinarily
    1.88
     
    1.85
     considerably
    1.81
    Activations Density 0.003%

    No Known Activations