© 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. 34-GEMMASCOPE-RES-131K
    4. 119314
    Prev
    Next
    INDEX
    Explanations

    policy and research institutions

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

    This neuron activates on formal named entities—especially organization, institution, and think-tank names (and related titles).

    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
     UNICEF
    -0.80
    TOTAL
    -0.79
    íritu
    -0.77
     表
    -0.75
    ymas
    -0.73
    вля
    -0.73
     техні
    -0.73
     '\\;'
    -0.72
    atrician
    -0.71
    WHEREAS
    -0.71
    POSITIVE LOGITS
     think
    1.82
     analysts
    1.66
     policy
    1.59
     Policy
    1.47
     анали
    1.45
     analyst
    1.43
     analysis
    1.41
    analy
    1.39
    policy
    1.34
     strategic
    1.33
    Activations Density 0.056%

    No Known Activations