© 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. 86879
    Prev
    Next
    INDEX
    Explanations

    senior citizen roles

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

    The neuron is primarily triggered by the word “Senior” (especially as part of titles or program names).

    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
     Rússia
    -0.91
     Welche
    -0.89
    都不是
    -0.79
    enaam
    -0.78
     clearness
    -0.78
    Tinh
    -0.78
    TEMPERATURE
    -0.77
    Symb
    -0.76
     Хар
    -0.75
     unfold
    -0.74
    POSITIVE LOGITS
     citizen
    2.16
     citizens
    1.81
    Citizen
    1.41
    citizen
    1.41
     Citizen
    1.27
    citizens
    1.21
     Citizens
    1.17
    Citizens
    1.16
    itis
    1.11
     senior
    1.02
    Activations Density 0.012%

    No Known Activations