© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    never been, ever seen/encountered

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

    This neuron detects the common phrase “never … been,” as in “has never been easier.”

    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
    sk
    0.77
    zeitig
    0.77
     нередко
    0.76
     banyaknya
    0.73
    س
    0.73
    m
    0.72
     ограничения
    0.71
    ة
    0.71
    कई
    0.69
     некоторые
    0.68
    POSITIVE LOGITS
     Με
    0.75
    ciences
    0.75
     stata
    0.72
    椭
    0.71
     such
    0.70
     jamás
    0.70
    ابقة
    0.69
     Bathroom
    0.66
     Đến
    0.66
    ιν
    0.65
    Activations Density 0.013%

    No Known Activations