© 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. 34-GEMMASCOPE-RES-131K
    7. 53947
    Prev
    Next
    INDEX
    Explanations

    president or chairman positions

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

    The neuron is tuned to detect mentions of official roles or titles (e.g. “president,” “served as …,” “Association”) in an organization or institution.

    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
    staff
    -0.79
    relser
    -0.75
    ukses
    -0.72
    partner
    -0.71
    posy
    -0.70
     групи
    -0.69
    ıt
    -0.69
    status
    -0.68
    hopal
    -0.68
    senz
    -0.67
    POSITIVE LOGITS
     president
    5.50
     President
    4.50
    president
    4.13
    President
    4.03
     presidente
    3.52
     presidents
    3.50
     président
    3.38
     PRESIDENT
    3.31
     chairman
    3.22
    PRESIDENT
    2.98
    Activations Density 0.053%

    No Known Activations