© 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. 74403
    Prev
    Next
    INDEX
    Explanations

    wage increase and growth

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

    This neuron activates on occurrences of the term “wage” (and its plural) especially in contexts with numerical amounts or changes.

    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
    手里的
    -3.13
    敉
    -2.88
    他就
    -2.77
    珦
    -2.77
    身边的
    -2.66
    神
    -2.53
    軚
    -2.52
    堙
    -2.50
    ężczy
    -2.48
    
    -2.47
    POSITIVE LOGITS
     These
    2.88
    ↵↵
    2.81
    是啊
    2.63
    e
    2.47
    可能
    2.39
    L
    2.30
     Their
    2.27
    b
    2.23
     vand
    2.22
    是
    2.16
    Activations Density 0.003%

    No Known Activations