© 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. 22-GEMMASCOPE-RES-131K
    7. 66255
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    The neuron strongly activates on numeric tokens (dates, times, measurements, coordinates, etc.), i.e. it detects numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     for
    -0.94
     first
    -0.93
     many
    -0.92
    月の
    -0.88
    quiera
    -0.85
     any
    -0.85
    品です
    -0.85
     it
    -0.84
     truk
    -0.83
     skr
    -0.82
    POSITIVE LOGITS
    ícia
    1.00
     てる
    0.93
    création
    0.92
     emporter
    0.91
    conium
    0.87
    ranes
    0.87
    Ļ
    0.86
     {}
    0.85
     behandel
    0.84
     layman
    0.84
    Activations Density 0.057%

    No Known Activations