© 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. 34938
    Prev
    Next
    INDEX
    Explanations

    price and affordability

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

    The neuron activates on words and phrases that refer to pricing or cost (e.g. “price,” “how much is it,” “discount,” “reasonable price,” “cheap”).

    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
     improving
    -0.96
    返品
    -0.91
     improve
    -0.88
    зопас
    -0.86
     dõi
    -0.83
    tifully
    -0.80
    用語
    -0.79
    しくて
    -0.79
     schlechte
    -0.79
    TRAILING
    -0.78
    POSITIVE LOGITS
     price
    1.54
     affordable
    1.48
     affordability
    1.26
     cheap
    1.13
     prices
    1.13
    affordable
    1.11
     Affordable
    1.10
     cheaper
    1.09
     range
    1.07
     budget
    1.05
    Activations Density 0.013%

    No Known Activations