© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101285
    Prev
    Next
    INDEX
    Explanations

    trading company, vessel, partners, IT

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

    the word "Trading" when it appears as part of a proper noun or company name.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron consistently spikes on the token “Trading,” so it’s detecting occurrences of the word “trading.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ’
    -3.23
    癶
    -2.41
    1
    -2.41
    “
    -2.22
    两个人
    -2.19
     Konkur
    -2.19
    她就
    -2.16
     es
    -2.16
    ឵
    -2.16
    早已
    -2.14
    POSITIVE LOGITS
    鴣
    2.91
    
    2.77
    葙
    2.66
    賔
    2.48
    瑧
    2.41
    凝土
    2.39
     tomadas
    2.31
    镭
    2.30
    ve
    2.28
    姈
    2.28
    Activations Density 0.003%

    No Known Activations