© 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. 34-GEMMASCOPE-RES-131K
    7. 65139
    Prev
    Next
    INDEX
    Explanations

    constitution and related governmental structures

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

    This neuron detects references to a (national) constitution, especially mentions of a specific country’s constitution.

    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
     testifying
    -0.77
     Celebrity
    -0.76
    AFX
    -0.75
    iertos
    -0.74
     と
    -0.74
    CDK
    -0.72
     新品
    -0.71
     神
    -0.69
     Siemens
    -0.69
    
    -0.68
    POSITIVE LOGITS
     Constitution
    5.69
     constitution
    4.94
    Constitution
    4.78
     CONSTITUTION
    3.28
     constitutional
    3.28
     constitutions
    3.14
     Constitución
    2.95
     Constitu
    2.72
    憲法
    2.67
     Constitutional
    2.53
    Activations Density 0.039%

    No Known Activations