© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    numeric or symbol sequences

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

    This neuron fires on words denoting commercial transactions or e-commerce offerings (e.g., shopping, drugs, flights).

    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
     improvised
    0.79
    varian
    0.78
     разработан
    0.77
     погиб
    0.77
    🙉
    0.74
     demolished
    0.73
     begged
    0.73
    Debit
    0.73
     предназначен
    0.71
     impregnated
    0.71
    POSITIVE LOGITS
    س
    0.75
    おります
    0.67
    とい
    0.67
    स
    0.66
    理
    0.65
    ところ
    0.64
    理性
    0.64
    त
    0.64
     nombreux
    0.64
    ڕۆ
    0.64
    Activations Density 0.000%

    No Known Activations