© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7230
    Prev
    Next
    INDEX
    Explanations

    donate or donation

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

    The neuron strongly activates on mentions of donation solicitations and the associated monetary amounts or numeric fundraising details.

    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
    FETCH
    0.57
     FETCH
    0.55
    ಲ್
    0.55
     كي
    0.52
    ዝ
    0.51
    قى
    0.50
     Maiden
    0.50
     Garry
    0.50
     مشروع
    0.50
     пози
    0.50
    POSITIVE LOGITS
     donations
    2.02
     donation
    1.96
     donate
    1.92
     donating
    1.90
    donation
    1.78
     Donations
    1.74
    donate
    1.74
     Donation
    1.72
     donated
    1.69
    捐
    1.63
    Activations Density 0.144%

    No Known Activations