© 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. 946
    Prev
    Next
    INDEX
    Explanations

    `FL.`, `her`, `isk`

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

    The main thing this neuron does is detect names or words containing Scandinavian‐style diacritics (e.g. ø, å) and other non-ASCII letters.

    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
     dolayı
    0.68
    rpt
    0.68
    .¹
    0.63
    .³
    0.63
    zmq
    0.62
    cito
    0.61
    gf
    0.60
     jurisdict
    0.59
    c
    0.59
     [[
    0.59
    POSITIVE LOGITS
    ﻮ
    0.67
    ון
    0.66
    ardt
    0.63
    ified
    0.63
    ruptcy
    0.63
    elyn
    0.63
    ण्डी
    0.62
    રે
    0.62
    ótica
    0.62
    osphère
    0.62
    Activations Density 1.142%

    No Known Activations