© 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. 92192
    Prev
    Next
    INDEX
    Explanations

    Bethlehem and names like Beth

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

    This neuron strongly activates on occurrences of the place name “Bethlehem.”

    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
    ྭ
    -0.71
    のだろう
    -0.70
    没办法
    -0.69
    یا
    -0.68
     Vicki
    -0.67
    भव
    -0.66
     blunder
    -0.66
     effectuer
    -0.66
    eti
    -0.66
     benthic
    -0.65
    POSITIVE LOGITS
    التالي
    0.81
     росій
    0.77
     Steel
    0.75
     Однако
    0.72
    యు
    0.72
    gatsby
    0.70
     Easy
    0.69
    glise
    0.69
     oliver
    0.69
    ร้าน
    0.68
    Activations Density 0.024%

    No Known Activations