© 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. 8781
    Prev
    Next
    INDEX
    Explanations

    words in various asian languages

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

    The neuron strongly activates on personal proper names (people’s names).

    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
    Aslamualaikum
    0.64
    แตกต่าง
    0.64
     lohnt
    0.62
    መሳሳይ
    0.61
     ניתן
    0.61
     sommige
    0.61
    Ϥ
    0.61
     //[
    0.59
    נגלית
    0.59
     большинство
    0.57
    POSITIVE LOGITS
    さんが
    0.90
    さんと
    0.89
    ちゃん
    0.82
    さんの
    0.81
    さんに
    0.81
    等人
    0.80
    さん
    0.76
    さんも
    0.76
    한테
    0.75
    ちゃんの
    0.73
    Activations Density 0.093%

    No Known Activations