© 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. 22-GEMMASCOPE-RES-131K
    7. 75355
    Prev
    Next
    INDEX
    Explanations

    cities and places

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

    The neuron strongly activates on geographic place names (cities, regions, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    的存在
    -0.99
     撮
    -0.96
     هوش
    -0.94
    Năm
    -0.91
    quedas
    -0.90
    ủng
    -0.90
    衚
    -0.90
    oasis
    -0.89
    več
    -0.88
    းက
    -0.88
    POSITIVE LOGITS
    は
    1.05
    を
    0.96
    你去
    0.92
     кръ
    0.88
    \_
    0.86
    で
    0.84
    你和
    0.82
     "
    0.82
    g
    0.81
    
    0.81
    Activations Density 0.165%

    No Known Activations