© 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. 1136
    Prev
    Next
    INDEX
    Explanations

    multilingual introductory words

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

    The neuron strongly activates on blocks of Irish‐language text (Gaelic words and accented characters), flagging passages written in that foreign language.

    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
     ಹಾಗೂ
    0.83
     bzw
    0.63
     혹은
    0.62
     czyli
    0.55
     الى
    0.54
     ataupun
    0.54
     তথা
    0.54
    ־
    0.52
     golongan
    0.52
     તથા
    0.51
    POSITIVE LOGITS
     splicing
    0.67
     použití
    0.64
     adsorption
    0.61
     möglicherweise
    0.61
     centrifugation
    0.60
     voxel
    0.60
     adsorbed
    0.59
    应用程序
    0.59
     birefringence
    0.59
     copolymer
    0.58
    Activations Density 0.104%

    No Known Activations