© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48229
    Prev
    Next
    INDEX
    Explanations

    brand names and drugs

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

    brand and product names, particularly in pharmaceuticals and technology companies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is sensitive to proper brand or product names (trademarks) appearing in the text.

    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
    a
    -2.75
    </sup>
    -2.31
    ents
    -2.17
    </h2>
    -2.08
    		
    -2.06
    </h4>
    -2.03
    无论是
    -2.00
    izes
    -1.98
    无论
    -1.98
     are
    -1.96
    POSITIVE LOGITS
    鈈
    2.69
     motocicletas
    2.58
     helicópter
    2.50
    
    2.17
     stär
    2.17
     fotógrafo
    2.16
     helicóptero
    2.14
    拶
    2.13
     salieron
    2.08
     tuvimos
    2.08
    Activations Density 0.003%

    No Known Activations