© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11026
    Prev
    Next
    INDEX
    Explanations

    foreign currency amounts

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

    The neuron fires strongly on uncommon, low‐frequency content words (e.g. technical terms, proper nouns, and rare vocabulary).

    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
    こちらの
    0.76
    示
    0.72
    皆様
    0.71
    РС
    0.69
    什么是
    0.67
    بك
    0.67
    宇
    0.66
    延续
    0.66
    ったり
    0.66
    references
    0.66
    POSITIVE LOGITS
     Kräfte
    0.94
     WOR
    0.86
     livello
    0.84
     pfl
    0.83
    Trails
    0.81
    рии
    0.80
     stai
    0.78
     जे
    0.77
     mellom
    0.77
     акысыз
    0.77
    Activations Density 0.001%

    No Known Activations