© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68142
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron fires on numeric date/time tokens—especially four-digit year values in timestamps.

    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
     and
    -2.36
     has
    -1.84
     for
    -1.73
    After
    -1.73
     if
    -1.69
     should
    -1.65
    六年
    -1.63
     as
    -1.63
     in
    -1.62
     will
    -1.59
    POSITIVE LOGITS
    阏
    1.92
    ≜
    1.70
    provides
    1.67
     diriger
    1.66
     produire
    1.63
     frequentemente
    1.62
     développer
    1.59
     conduire
    1.58
    拍了拍
    1.57
    kinda
    1.53
    Activations Density 0.021%

    No Known Activations