© 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. 25722
    Prev
    Next
    INDEX
    Explanations

    ancient Celtic tribes and history

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

    The neuron specializes in spotting numeric tokens (e.g. years, measurements, or any digit‐containing terms).

    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
    igma
    -0.83
     błę
    -0.75
     sistemas
    -0.73
     Colombia
    -0.73
    ègre
    -0.73
    žno
    -0.69
    canada
    -0.69
    pertise
    -0.68
    IMIENTO
    -0.68
     Greek
    -0.67
    POSITIVE LOGITS
     Celtic
    1.30
     druid
    1.29
     Druid
    1.20
     Gaul
    1.10
    Celtic
    1.09
     tribes
    1.06
     tribal
    1.02
     celtic
    0.96
     tribe
    0.96
     Britannia
    0.95
    Activations Density 0.019%

    No Known Activations