© 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. 22-GEMMASCOPE-RES-131K
    4. 92933
    Prev
    Next
    INDEX
    Explanations

    currency trading

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

    The neuron detects fragments of commercial website URLs or online store domain names (e.g. currency-trading and pharmacy site names).

    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
     all
    -1.07
     at
    -1.04
     for
    -0.96
     so
    -0.95
     &
    -0.91
     quite
    -0.91
     where
    -0.90
     on
    -0.88
     change
    -0.84
    ,
    -0.83
    POSITIVE LOGITS
     bloquer
    1.05
    ounid
    0.98
     ValidationError
    0.97
     menangis
    0.97
     ralenti
    0.96
    Noch
    0.95
    Puedes
    0.94
    Ό
    0.94
     encanta
    0.94
    Penjelasan
    0.94
    Activations Density 0.011%

    No Known Activations