© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    majority

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

    This neuron is strongly activated by the word “majority.”

    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
     tota
    0.65
    EM
    0.63
    رك
    0.61
    ausa
    0.61
    总
    0.61
    entuk
    0.60
    总量
    0.60
    ұ
    0.59
    ้ม
    0.59
     шт
    0.56
    POSITIVE LOGITS
     shareholder
    0.87
    Majority
    0.84
     большинстве
    0.81
     Majority
    0.80
     majority
    0.78
    多数
    0.78
    majority
    0.77
     maioria
    0.76
     większość
    0.74
     большинства
    0.71
    Activations Density 0.070%

    No Known Activations