© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    Filipino words and phrases

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

    The neuron selectively activates on Tagalog (Filipino) words and morphemes in the text.

    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
     sør
    0.55
     (*)
    0.51
     Việt
    0.50
     trink
    0.50
     består
    0.48
     lehető
    0.47
     zove
    0.47
    hv
    0.47
     Noeud
    0.47
     Thé
    0.46
    POSITIVE LOGITS
     ngayon
    0.75
     iyong
    0.73
     nila
    0.71
     yung
    0.70
     naman
    0.69
    啊
    0.69
     lamang
    0.69
     ng
    0.67
     niya
    0.66
     umano
    0.65
    Activations Density 0.017%

    No Known Activations