© 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. 93816
    Prev
    Next
    INDEX
    Explanations

    cultural traditions and heritage

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

    This neuron is highly sensitive to numeric and enumerative tokens—years, page or list numbers, counts, and similar digit‐based markers.

    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
     grayscale
    -0.78
     Karena
    -0.76
     ELF
    -0.74
    zkopf
    -0.74
    thodon
    -0.71
    Tennis
    -0.71
    cová
    -0.71
    TRACE
    -0.71
     grunge
    -0.70
    DataAccess
    -0.69
    POSITIVE LOGITS
     intangible
    1.70
    intang
    1.38
     UNESCO
    1.32
     Int
    1.10
     traditional
    1.09
     ICH
    1.05
     Traditional
    1.05
     Tradition
    1.00
    UNESCO
    1.00
    ICH
    0.98
    Activations Density 0.011%

    No Known Activations