© 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. 32978
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

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

    The neuron is detecting numeric tokens—especially multi‐digit sequences used in dates, times, offsets, and other numeric metadata.

    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
     Associates
    -0.82
    mbros
    -0.82
    ecznie
    -0.78
    alians
    -0.78
    
    -0.77
     WATCH
    -0.76
     simulated
    -0.75
    daan
    -0.75
     czę
    -0.73
    过了
    -0.72
    POSITIVE LOGITS
    kett
    0.80
    flexGrow
    0.74
    ientes
    0.72
     niềm
    0.71
     carvings
    0.71
     Surplus
    0.69
     Matrices
    0.68
     Lying
    0.67
    やすく
    0.66
    Время
    0.66
    Activations Density 0.031%

    No Known Activations