© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82458
    Prev
    Next
    INDEX
    Explanations

    Japanese names

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

    The neuron is strongly activated by romanized Japanese proper names (personal names and place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    薗
    -1.07
    嵜
    -1.02
     滝
    -0.93
    鴎
    -0.88
    Sushi
    -0.84
    業界
    -0.81
     戸
    -0.80
    JAPAN
    -0.79
    五郎
    -0.79
     鶴
    -0.78
    POSITIVE LOGITS
     |]
    0.90
     splet
    0.89
     retain
    0.89
    ⟺
    0.88
    (=)
    0.86
    nai
    0.85
     vincit
    0.84
    eda
    0.84
     "../../../../
    0.81
    oda
    0.80
    Activations Density 0.057%

    No Known Activations