© 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. 59179
    Prev
    Next
    INDEX
    Explanations

    Eastern Front or World War

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

    The neuron strongly activates on multi-digit numeric tokens—especially dates, years, and other large numbers.

    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
    Julia
    -0.73
     prov
    -0.73
    市内
    -0.73
    phur
    -0.73
     cỏ
    -0.71
    Gia
    -0.70
     proximal
    -0.69
    aç
    -0.69
     Hes
    -0.69
    спор
    -0.69
    POSITIVE LOGITS
     Verdun
    1.24
     CDP
    0.88
     MEMBERSHIP
    0.84
     Brus
    0.80
    gapan
    0.75
    Índice
    0.74
     Danke
    0.74
    浸
    0.73
    Brus
    0.73
     Caramel
    0.71
    Activations Density 0.034%

    No Known Activations