© 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. 39483
    Prev
    Next
    INDEX
    Explanations

    historical periods and eras

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

    The neuron specializes in picking out numeric references to historical time periods—years, dynasties, centuries, and era names.

    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
     for
    -2.50
     they
    -1.80
     from
    -1.58
     aapt
    -1.55
     at
    -1.50
     PARAMETER
    -1.48
    还真
    -1.47
     a
    -1.47
    verter
    -1.46
    titial
    -1.39
    POSITIVE LOGITS
    Before
    1.48
    Between
    1.45
     Before
    1.45
    கா
    1.38
     period
    1.38
     beschränkt
    1.37
     aislada
    1.36
     consiguiente
    1.35
    Jawaban
    1.32
    During
    1.30
    Activations Density 0.062%

    No Known Activations