© 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. 7125
    Prev
    Next
    INDEX
    Explanations

    chote baccho ke

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

    The neuron strongly activates on sequences of Irish‐Gaelic text (i.e. words with the acute‐accented characters and orthography typical of Gaelic).

    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
     при
    0.75
     slechts
    0.73
     camino
    0.71
     ¨
    0.71
     colaboradores
    0.71
     quer
    0.71
     recl
    0.71
     nacht
    0.71
     hånd
    0.71
     lässt
    0.69
    POSITIVE LOGITS
    佢
    0.94
    喺
    0.92
     Fransiya
    0.82
    icions
    0.79
    嘅
    0.75
    咗
    0.74
     Medicines
    0.73
     Mainly
    0.73
    啲
    0.71
    嚟
    0.69
    Activations Density 0.093%

    No Known Activations