© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4709
    Prev
    Next
    INDEX
    Explanations

    requesting input or instructions

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

    The neuron fires on polite help‐seeking or suggestion‐request phrases (e.g. “advice,” “suggestion,” “appreciated,” “appreciate”).

    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_24_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
    чности
    0.77
    샀
    0.76
     거고
    0.75
     szczę
    0.68
     недостаточно
    0.67
     জিনিস
    0.66
     nisam
    0.66
     이것
    0.64
     quên
    0.64
     근데
    0.63
    POSITIVE LOGITS
     please
    0.86
    please
    0.86
    または
    0.85
    もしくは
    0.84
     preferably
    0.79
    或
    0.79
     either
    0.78
     kindly
    0.78
    あるいは
    0.75
    either
    0.75
    Activations Density 0.281%

    No Known Activations