© 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. 38047
    Prev
    Next
    INDEX
    Explanations

    Jee, Ji, Zhi

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

    The neuron fires on occurrences of the specific token “Ji,” as it appears in romanized Chinese names or terms.

    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
    力を
    -0.82
    ┌
    -0.82
     particuli
    -0.81
    ＼
    -0.77
     habitantes
    -0.75
     Fluids
    -0.75
     légitime
    -0.74
    setY
    -0.74
     sete
    -0.73
    EVER
    -0.73
    POSITIVE LOGITS
    нак
    0.83
     najlepiej
    0.81
    dge
    0.81
    Trainer
    0.79
    รวม
    0.77
    тью
    0.77
     Konst
    0.77
     minuti
    0.76
    MESH
    0.75
     ähn
    0.74
    Activations Density 0.007%

    No Known Activations