© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49559
    Prev
    Next
    INDEX
    Explanations

    Mennonite culture

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

    The neuron strongly activates on capitalized geographic or community proper names (e.g. place or colony names).

    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
     priest
    -0.82
     priests
    -0.76
    tablet
    -0.75
    xygen
    -0.74
    Cyl
    -0.73
     servis
    -0.73
    ַּ
    -0.73
     mummy
    -0.72
    pera
    -0.71
     doses
    -0.70
    POSITIVE LOGITS
     Amish
    2.58
     Mennon
    1.35
     buggy
    1.26
     Ordnung
    1.10
    Lancaster
    1.05
     Lancaster
    0.99
     shunned
    0.92
     Pennsylvania
    0.91
     Buggy
    0.90
    Plain
    0.90
    Activations Density 0.010%

    No Known Activations