© 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. 10-GEMMASCOPE-RES-131K
    7. 9041
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    The neuron activates on numeric tokens—any standalone numbers, including dates, times, measurements, or other digit sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    including
    -1.72
    even
    -1.52
    Including
    -1.49
     ">=
    -1.48
     bahkan
    -1.47
     می‌شوند
    -1.46
    䌀
    -1.45
     inteligen
    -1.41
    this
    -1.40
    包括
    -1.40
    POSITIVE LOGITS
     it
    1.63
     merkezi
    1.34
     something
    1.31
    Bypass
    1.30
     elegancia
    1.28
     imbued
    1.25
    Twas
    1.23
     
    1.23
     each
    1.21
    colección
    1.21
    Activations Density 0.028%

    No Known Activations