© 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. 31-GEMMASCOPE-2-RES-16K
    7. 557
    Prev
    Next
    INDEX
    Explanations

    binary addition

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

    The neuron strongly activates on economic and financial terms (e.g. inflation, prices, costs, rates).

    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_31_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
    此外
    0.54
    এক
    0.48
    Под
    0.47
    Дру
    0.47
    Ва
    0.46
    这意味着
    0.46
    龺
    0.45
    इसमें
    0.44
    Ꭺ
    0.44
     এছাড়াও
    0.43
    POSITIVE LOGITS
     ditulis
    0.44
     sonra
    0.43
     kuin
    0.43
     gjort
    0.41
     eller
    0.40
    .:
    0.40
     kontrol
    0.39
     angegeben
    0.39
     gemaakt
    0.39
    gota
    0.38
    Activations Density 2.790%

    No Known Activations