© 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. 22-GEMMASCOPE-RES-131K
    7. 38977
    Prev
    Next
    INDEX
    Explanations

    high cost price

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

    The neuron identifies terms and phrases that convey high cost or expense (e.g. “pricey,” “expensive,” “overpriced”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    　　[
    -1.02
     беспла
    -0.98
    💪
    -0.97
    osuke
    -0.94
     airbags
    -0.90
     cerita
    -0.86
    ތ
    -0.86
    phalt
    -0.86
    安い
    -0.85
    🤘
    -0.85
    POSITIVE LOGITS
     expensive
    1.91
     Expensive
    1.54
    Expensive
    1.52
     pricey
    1.45
     price
    1.39
     prices
    1.28
     ($
    1.22
     costly
    1.17
    expensive
    1.13
     expense
    1.08
    Activations Density 0.033%

    No Known Activations