© 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. 34-GEMMASCOPE-RES-131K
    7. 31805
    Prev
    Next
    INDEX
    Explanations

    up to date

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

    This neuron detects occurrences of the phrase “up to date” (including its broken-out tokens).

    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
     fontos
    -1.21
     csal
    -1.19
     nyug
    -0.99
     színes
    -0.96
     munka
    -0.96
     biztons
    -0.96
     hű
    -0.95
     tény
    -0.93
     szüks
    -0.93
     mindig
    -0.90
    POSITIVE LOGITS
     to
    3.23
     date
    1.68
    to
    1.20
    ToDate
    1.12
    date
    1.09
     dated
    1.05
    Date
    1.05
     Date
    1.00
     To
    0.94
    To
    0.90
    Activations Density 0.009%

    No Known Activations