© 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. 23830
    Prev
    Next
    INDEX
    Explanations

    Indian followed by specific entities

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

    The neuron specifically fires on occurrences of the word “Indian” (especially when it’s part of an organization or proper name).

    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
    nor
    -0.91
    あります
    -0.83
    anueva
    -0.79
     I
    -0.78
    収穫
    -0.76
    imat
    -0.75
     amd
    -0.73
    tf
    -0.73
    立马
    -0.73
    полнитель
    -0.69
    POSITIVE LOGITS
     Ocean
    1.02
    🇮
    1.02
    express
    1.00
    ('=
    0.98
    Indian
    0.96
     Express
    0.94
     continent
    0.94
    esse
    0.94
     reservation
    0.94
    scenario
    0.92
    Activations Density 0.014%

    No Known Activations