© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14182
    Prev
    Next
    INDEX
    Explanations

    followed by verbs (ni)

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

    This neuron primarily detects Japanese text segments (Japanese characters and tokens).

    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_24_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
    м
    1.00
    ка
    0.94
    ся
    0.94
    для
    0.94
    า
    0.84
    ة
    0.81
    й
    0.80
    дон
    0.80
    theless
    0.78
    вы
    0.78
    POSITIVE LOGITS
     의해
    0.76
    써
    0.73
     대해
    0.70
     는
    0.69
     비해
    0.68
     부터
    0.67
     Já
    0.66
     대해서
    0.66
     의한
    0.66
     인해
    0.65
    Activations Density 0.001%

    No Known Activations