© 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. 19277
    Prev
    Next
    INDEX
    Explanations

    lavish luxurious sumptuous extravagant

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

    The neuron fires on rich, hyperbolic adjectives that convey luxury, opulence, sensuality, or sumptuousness.

    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
    鍇
    -2.33
     retira
    -2.19
    棪
    -2.17
     exercí
    -2.16
    玏
    -2.14
    esomeness
    -2.13
    罽
    -2.09
    ⸎
    -2.08
    ໋
    -2.08
     saati
    -2.08
    POSITIVE LOGITS
    .
    2.50
     queste
    2.44
    a
    2.41
    :"
    2.27
          
    2.22
    ?"
    2.17
    ؟
    2.11
    ="
    2.09
    </b>
    2.09
     "
    2.08
    Activations Density 0.003%

    No Known Activations