© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    salaries or financial figures in India

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

    This neuron responds to longer, multisyllabic content words (e.g. “light,” “discussions,” “overcoming,” “solutions”) that carry informational weight.

    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
     一个
    0.62
    죤
    0.62
     bellow
    0.62
    ine
    0.60
     什么
    0.60
    尓
    0.59
     sufferer
    0.58
     century
    0.56
    :-
    0.56
     Otherwise
    0.56
    POSITIVE LOGITS
     onboarding
    0.90
     omnichannel
    0.89
     reimag
    0.86
     inclusivity
    0.83
     curated
    0.80
     fintech
    0.80
    、『
    0.79
     whatnot
    0.79
    📍
    0.78
     coworking
    0.77
    Activations Density 0.087%

    No Known Activations