© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73619
    Prev
    Next
    INDEX
    Explanations

    Indian surnames

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

    This neuron activates on tokens that are parts of proper names, especially Indian personal 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
    보
    -0.83
    ジャケット
    -0.75
     ある
    -0.75
     organism
    -0.75
     ジャケット
    -0.75
    idle
    -0.74
    铂
    -0.72
    Discussion
    -0.72
     моро
    -0.71
    Nella
    -0.71
    POSITIVE LOGITS
    otra
    1.01
    putar
    0.94
    ACIAS
    0.94
    helia
    0.91
     Tuhan
    0.91
     Ін
    0.90
    stützung
    0.88
    に行った
    0.88
    pleaños
    0.87
    所在的
    0.87
    Activations Density 0.029%

    No Known Activations