© 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. 546
    Prev
    Next
    INDEX
    Explanations

    bidding and procurement process

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

    The neuron detects terms related to bidding and tender processes (e.g. bid, bidding, tender, contract, auction).

    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
     erläut
    -0.84
    فظ
    -0.80
    含量
    -0.77
    粉
    -0.72
     albicans
    -0.72
    雇
    -0.71
     INDUSTRIES
    -0.71
    四人
    -0.71
     xã
    -0.71
    ിച്ച
    -0.70
    POSITIVE LOGITS
     documents
    1.43
    Documents
    1.21
     documentos
    1.17
    documents
    1.13
     Documents
    1.09
     document
    1.05
     Dokumente
    0.95
     DOCUMENTS
    0.90
     process
    0.90
    DOC
    0.89
    Activations Density 0.011%

    No Known Activations