© 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. 8515
    Prev
    Next
    INDEX
    Explanations

    fundraising and donations

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

    The neuron is detecting words and phrases related to charitable giving and fundraising.

    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
    核
    0.55
     wastes
    0.52
    ὤ
    0.52
    핵
    0.52
    𐰇
    0.52
    ἃ
    0.52
    enteri
    0.50
     সার্ভিস
    0.50
     れ
    0.50
     nuclé
    0.50
    POSITIVE LOGITS
     fundraising
    2.77
     Fundraising
    2.69
     fundraisers
    2.50
     fundraiser
    2.47
     donations
    2.28
    捐
    2.25
     donation
    2.17
     donors
    2.14
     donor
    2.11
     donate
    2.03
    Activations Density 0.606%

    No Known Activations