© 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. 87059
    Prev
    Next
    INDEX
    Explanations

    collaborative partnerships and work

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

    The main thing this neuron does is find words and phrases indicating collaboration or cooperation (e.g., “collaborative,” “cooperative,” “partnership”).

    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
    也只是
    -0.84
     нещо
    -0.75
    只是一个
    -0.73
     мероприятий
    -0.72
    ございません
    -0.72
     menino
    -0.70
     capitolo
    -0.70
     dolayı
    -0.70
    也算
    -0.70
     كوم
    -0.69
    POSITIVE LOGITS
     APPROACH
    1.06
     approach
    1.05
    学习
    1.01
     effort
    0.99
     venture
    0.93
    写作
    0.93
     authorship
    0.92
     learning
    0.90
    Filtering
    0.88
     workspace
    0.88
    Activations Density 0.019%

    No Known Activations