© 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. 10-GEMMASCOPE-RES-131K
    7. 119673
    Prev
    Next
    INDEX
    Explanations

    wireless communication

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

    the word "Wireless" in technical patent documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    書いて
    -2.59
     {
    -2.48
     tienen
    -2.47
     «
    -2.44
     OF
    -2.39
     
    -2.38
    进了
    -2.34
    t
    -2.30
     sigue
    -2.25
    更高
    -2.23
    POSITIVE LOGITS
    媗
    3.50
    酲
    2.95
    趼
    2.94
     parachoque
    2.92
    脔
    2.84
    鷓
    2.78
    鱘
    2.78
    that
    2.75
    ೢ
    2.69
    櫺
    2.66
    Activations Density 0.007%

    No Known Activations