© 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. 103588
    Prev
    Next
    INDEX
    Explanations

    Google products and services

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

    The neuron fires on proper names of tech products and companies (especially “Google” and its product names).

    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
    mern
    -0.75
     esco
    -0.72
     *
    -0.71
    ("")){
    -0.69
    Mer
    -0.68
    フォーマンス
    -0.67
     afterward
    -0.67
    NIS
    -0.67
    {?>
    -0.66
     tile
    -0.66
    POSITIVE LOGITS
     hangout
    0.97
     Guelph
    0.85
     Wimbledon
    0.81
     Gmail
    0.78
     Nexus
    0.77
    namefont
    0.77
     polymeric
    0.77
     TPU
    0.76
     Willem
    0.74
     Baroness
    0.74
    Activations Density 0.121%

    No Known Activations