© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    people of regions or countries

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

    The neuron responds to words referring to the general public or populace (e.g. “people,” “populace”).

    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
     herkes
    -1.09
    大概是
    -1.02
     افراد
    -0.97
    Everyone
    -0.94
     individuals
    -0.93
    varlak
    -0.92
     Gründe
    -0.91
     families
    -0.91
    大概
    -0.90
     prestigious
    -0.90
    POSITIVE LOGITS
     of
    1.91
     themselves
    1.05
     dataGridView
    0.94
    hood
    0.93
     inhabiting
    0.92
    folk
    0.89
     who
    0.88
    ø
    0.86
     travaillons
    0.84
     ultimi
    0.81
    Activations Density 0.016%

    No Known Activations