© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    Burma, Bengal, Rohingya, Aung

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

    The neuron activates on numeric tokens (years, ordinal numbers, and other digit sequences).

    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
    晚安
    -0.78
    CHAPTER
    -0.76
     перегово
    -0.75
    硝
    -0.73
     CDU
    -0.73
    வா
    -0.72
    PN
    -0.71
    砥
    -0.71
    vaal
    -0.70
     заба
    -0.70
    POSITIVE LOGITS
     Rohing
    1.96
     Myanmar
    1.53
    Roh
    1.45
     Burmese
    1.44
    Myanmar
    1.34
     Burma
    1.27
     NF
    1.16
     Aung
    1.08
     Bengali
    1.01
     Bangladesh
    0.95
    Activations Density 0.024%

    No Known Activations