© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7377
    Prev
    Next
    INDEX
    Explanations

    found/obtained

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

    The main thing this neuron does is find words or phrases indicating the availability or purchase of a product.

    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
     Realty
    0.76
     horarios
    0.75
     banderas
    0.73
     fatorial
    0.71
     Futebol
    0.70
     Usuarios
    0.69
     Juegos
    0.69
     ﷺ
    0.68
     Volleyball
    0.67
     Igreja
    0.66
    POSITIVE LOGITS
     suppliers
    1.05
     supplier
    0.98
    supplier
    0.98
    suppliers
    0.95
     erhältlich
    0.94
     구입
    0.91
    ordered
    0.91
    obtained
    0.89
    obtain
    0.89
     diperoleh
    0.88
    Activations Density 0.350%

    No Known Activations