© 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. 81113
    Prev
    Next
    INDEX
    Explanations

    society or association names

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

    The neuron is specialized to detect mentions of formal organizations, societies, and conference/presentation contexts (e.g. professional association names and related details).

    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
     art
    -0.82
     arts
    -0.78
     engine
    -0.74
     Arts
    -0.73
    Indie
    -0.73
    してた
    -0.72
    ashion
    -0.72
    モーター
    -0.71
    してきました
    -0.71
     mill
    -0.71
    POSITIVE LOGITS
     Society
    1.95
     society
    1.72
    Society
    1.71
     societies
    1.70
    学会
    1.55
    society
    1.52
     Societies
    1.47
     SOCIETY
    1.45
     Association
    1.30
    Association
    1.30
    Activations Density 0.064%

    No Known Activations