© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14671
    Prev
    Next
    INDEX
    Explanations

    donations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ュー
    0.54
    executable
    0.52
    ዟ
    0.52
     Linguistic
    0.50
    Executable
    0.49
     kernel
    0.49
     ++)
    0.49
     cytokinin
    0.49
     beschäft
    0.49
    뮐
    0.48
    POSITIVE LOGITS
     donation
    4.91
     donations
    4.88
     donate
    4.81
     donating
    4.78
    捐
    4.59
     donated
    4.56
     Donations
    4.50
     Donation
    4.50
    donation
    4.31
     Donate
    4.25
    Activations Density 0.256%

    No Known Activations