© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16139
    Prev
    Next
    INDEX
    Explanations

    online marketplaces

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

    The neuron activates on mentions of company or professional organization names and titles (e.g. “Realtor,” “Better Business Bureau,” “Etsy,” “real estate agents,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    س
    0.80
    ج
    0.67
     Nh
    0.67
    فى
    0.67
     bowels
    0.63
    ک
    0.63
    جیت
    0.62
    ৩২
    0.62
     penso
    0.62
    ס
    0.62
    POSITIVE LOGITS
    자와
    0.90
     Advisors
    0.75
     조직
    0.72
     家具
    0.70
     extraordinaire
    0.69
    覦
    0.69
     statunitense
    0.68
     บริษัท
    0.67
     आणि
    0.66
     nationwide
    0.66
    Activations Density 0.004%

    No Known Activations