© 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. 90064
    Prev
    Next
    INDEX
    Explanations

    Taft-Hartley agreement

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

    The neuron fires on terms associated with labor‐union contract negotiations (e.g. union, tentative agreement, reached, wages, collective bargaining).

    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
     LOD
    -0.79
     bosques
    -0.78
    ؤال
    -0.77
     PET
    -0.74
    quait
    -0.73
    itais
    -0.73
     listy
    -0.72
    က်
    -0.71
     whispering
    -0.71
     Calcutta
    -0.70
    POSITIVE LOGITS
     bargaining
    1.29
     expired
    1.13
    labour
    1.06
     impasse
    1.03
     contract
    1.03
    Collective
    1.01
     agreement
    0.99
     negotiators
    0.98
     Collective
    0.95
     labour
    0.94
    Activations Density 0.020%

    No Known Activations