© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    phrase endings

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

    This neuron mainly activates on Japanese (Kanji) characters or character sequences.

    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
     majoring
    1.12
     ଅ
    1.09
    adə
    1.05
     ମ
    1.03
    ığımızda
    1.03
     ବି
    0.97
    ឡិច
    0.97
    ܠܐ
    0.95
     blemishes
    0.95
     və
    0.94
    POSITIVE LOGITS
    ん
    1.64
    じ
    1.55
    さ
    1.52
    い
    1.49
    っ
    1.46
    な
    1.45
    ま
    1.45
    や
    1.39
    っぱ
    1.38
    え
    1.37
    Activations Density 0.017%

    No Known Activations