© 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. 83688
    Prev
    Next
    INDEX
    Explanations

    place names and religious terms

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

    This neuron responds to tokens in highly structured, list-like or metadata sections (e.g. infoboxes or enumerated listings).

    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
     DNI
    -0.80
     ترام
    -0.77
     التع
    -0.75
    adla
    -0.73
     BOU
    -0.72
    besondere
    -0.72
     volledig
    -0.72
     itinéraires
    -0.72
     TCU
    -0.72
    strftime
    -0.71
    POSITIVE LOGITS
     Zion
    1.95
    Zion
    1.61
     Jerusalem
    1.26
     Egypt
    1.05
     Baptist
    1.02
    Jerusalem
    1.01
     Bethel
    1.01
    zion
    0.99
     Mount
    0.99
     Salem
    0.94
    Activations Density 0.025%

    No Known Activations