© 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. 10-GEMMASCOPE-RES-131K
    4. 111113
    Prev
    Next
    INDEX
    Explanations

    anatomical veins

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

    blood vessel terminology, particularly 'vein' and related anatomical terms.

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

    The neuron fires strongly on mentions of veins or venous structures (e.g., “vein,” “venous,” “intravenous,” “saphenous”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    
    -3.27
    ઁ
    -2.86
    ₶
    -2.86
    銦
    -2.58
    ;”
    -2.52
    ”;
    -2.47
    縯
    -2.42
    倨
    -2.38
    In
    -2.38
    赁
    -2.36
    POSITIVE LOGITS
     '
    3.48
    '
    3.47
     "
    2.48
     When
    2.34
     
    2.33
     เมื่อ
    2.31
    ↵↵
    2.27
    mathrm
    2.25
     retten
    2.16
      
    2.11
    Activations Density 0.015%

    No Known Activations