© 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. 10499
    Prev
    Next
    INDEX
    Explanations

    Estonia

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

    This neuron lights up on proper names and other named entities (people, places, organizations).

    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
    ssss
    0.73
    是
    0.73
    無い
    0.69
    给我
    0.67
     gives
    0.65
    很好的
    0.65
    说是
    0.64
    gives
    0.64
     дуже
    0.63
    は
    0.63
    POSITIVE LOGITS
     increasingly
    0.70
     ক্রমবর্ধমান
    0.70
     désormais
    0.70
    逐漸
    0.66
     באמצעות
    0.66
     newfound
    0.64
     zunehm
    0.62
     consapevole
    0.61
     commemorating
    0.59
     burgeoning
    0.59
    Activations Density 1.303%

    No Known Activations