© 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. 22-GEMMASCOPE-RES-131K
    7. 68913
    Prev
    Next
    INDEX
    Explanations

    last access or update time

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

    This neuron detects mentions of “last access time” metadata (e.g. tokens like “last Accessed Time” or similar timestamp field 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_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
    volezza
    -1.07
     primeiros
    -0.99
    AlreadyExists
    -0.98
    atmosfera
    -0.98
     seçenek
    -0.97
     окружающей
    -0.97
     ਲਈ
    -0.96
     namun
    -0.96
     genellikle
    -0.93
     mulai
    -0.93
    POSITIVE LOGITS
     last
    1.43
     recent
    1.30
     date
    1.20
     time
    1.16
     update
    1.13
     latest
    1.13
    RECENT
    1.11
     timeStamp
    1.07
     actualizada
    1.04
    最近
    1.01
    Activations Density 0.017%

    No Known Activations