© 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. 65024
    Prev
    Next
    INDEX
    Explanations

    religious and academic officer appointments

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

    The neuron flags the dates, formal offices, and institutional affiliations typical of a biographical entry (especially clergy careers).

    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
     MINISTER
    -0.85
     salade
    -0.84
     LEADER
    -0.82
     dapper
    -0.82
     luis
    -0.77
     آز
    -0.77
     blouses
    -0.77
    美しい
    -0.76
    codable
    -0.76
    aczy
    -0.76
    POSITIVE LOGITS
     canon
    1.20
     collegiate
    1.12
     bulls
    1.05
     Canon
    1.04
     canonical
    1.00
     dean
    0.94
     cathedral
    0.92
    canon
    0.90
     benef
    0.90
     reforma
    0.90
    Activations Density 0.066%

    No Known Activations