© 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. 80993
    Prev
    Next
    INDEX
    Explanations

    Gujarati Indian names

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

    The neuron strongly activates on tokens that are part of person names (proper‐noun name tokens).

    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
     alternatively
    -0.79
     pam
    -0.78
     alternativa
    -0.76
    ссор
    -0.71
    AspectRatio
    -0.70
    cm
    -0.70
    obie
    -0.69
     къ
    -0.68
    党
    -0.68
    gep
    -0.68
    POSITIVE LOGITS
     Bombay
    1.09
    walla
    1.02
    jee
    0.97
     Gujarati
    0.95
    wala
    0.94
    Bombay
    0.88
    racene
    0.82
     merchants
    0.81
     Gujarat
    0.81
     Merchants
    0.74
    Activations Density 0.030%

    No Known Activations