© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34983
    Prev
    Next
    INDEX
    Explanations

    dates

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

    The neuron fires on date and time tokens (month names, day-numbers, years, and related punctuation) in document headers or datelines.

    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
     Pří
    -1.09
     recherche
    -1.02
     like
    -0.94
    に見える
    -0.93
     many
    -0.90
    纜
    -0.89
     muerta
    -0.85
     from
    -0.85
     wiele
    -0.85
     рік
    -0.84
    POSITIVE LOGITS
    ષ
    1.14
    もありますが
    1.01
    žu
    1.00
    どちら
    0.99
     poë
    0.96
    がありますが
    0.96
    もありました
    0.94
    についても
    0.93
     meub
    0.92
    主要的
    0.92
    Activations Density 0.053%

    No Known Activations