© 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. 109183
    Prev
    Next
    INDEX
    Explanations

    sponsorship and shirt sponsor

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

    The neuron strongly activates on terms related to corporate or organizational sponsorship and 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
    스크
    -0.94
    boxer
    -0.90
    argout
    -0.83
    cías
    -0.80
    hermoso
    -0.80
    मे
    -0.79
    béco
    -0.78
     Coordin
    -0.78
    mockMvc
    -0.78
    kane
    -0.77
    POSITIVE LOGITS
     sponsorship
    2.61
     sponsor
    1.98
     sponsors
    1.95
     sponsoring
    1.88
     activation
    1.77
    Spons
    1.70
     Sponsorship
    1.57
    sponsor
    1.56
     activations
    1.41
     naming
    1.39
    Activations Density 0.021%

    No Known Activations