© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116069
    Prev
    Next
    INDEX
    Explanations

    company names ending in Co

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

    The neuron identifies corporate or organizational entity suffixes (like “Co,” “Inc,” “Corp,” “Company,” etc.).

    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
     like
    -0.95
    昨年
    -0.93
     include
    -0.92
     livelli
    -0.92
     super
    -0.87
    Superintendent
    -0.87
     різних
    -0.85
     require
    -0.85
     insisted
    -0.85
     either
    -0.84
    POSITIVE LOGITS
     Ltd
    1.24
    Ltd
    1.23
     pán
    1.05
     charmant
    1.05
    LTD
    1.03
     cesse
    1.02
     globales
    1.02
     stratég
    1.01
    .«
    1.01
     vernis
    1.00
    Activations Density 0.054%

    No Known Activations