© 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. 99240
    Prev
    Next
    INDEX
    Explanations

    dates and years

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

    The neuron detects multi‐digit numeric tokens—specifically the four-digit year numbers that appear in dates.

    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
    謄
    -0.90
    adır
    -0.77
     cerveza
    -0.77
    tabPage
    -0.76
    Arizona
    -0.75
    Biographie
    -0.75
    าสตร์
    -0.75
     Eggers
    -0.74
    örande
    -0.74
     Tempe
    -0.74
    POSITIVE LOGITS
    ql
    1.09
    yal
    1.09
    öl
    1.05
    äl
    1.05
     Joel
    1.01
     allele
    0.99
     июля
    0.99
    ral
    0.99
    ol
    0.96
    jal
    0.96
    Activations Density 0.150%

    No Known Activations