© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13018
    Prev
    Next
    INDEX
    Explanations

    please followed by a request

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

    The neuron strongly activates on polite request prompts—especially the word “Please.”

    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
     please
    1.27
    请
    1.16
    請
    1.16
     plz
    1.10
     pls
    1.02
    please
    0.99
     пожалуйста
    0.99
     請
    0.98
     lütfen
    0.98
     Please
    0.90
    POSITIVE LOGITS
    ؟!
    0.79
    őbb
    0.70
     (?)
    0.69
    racción
    0.68
    (?)
    0.67
     Macrom
    0.67
    씌
    0.67
    ٰ
    0.66
    viation
    0.65
    Notable
    0.65
    Activations Density 0.061%

    No Known Activations