© 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. 10-GEMMASCOPE-RES-131K
    7. 101736
    Prev
    Next
    INDEX
    Explanations

    year-month-day format

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

    The neuron detects numeric time stamps (digit sequences separated by colons) in text.

    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
     your
    -1.53
    饜
    -1.50
     différents
    -1.48
     joyería
    -1.48
     apprendre
    -1.44
     proposées
    -1.43
    ∓
    -1.42
    場で
    -1.41
     tatuaje
    -1.41
     deiner
    -1.39
    POSITIVE LOGITS
     без
    1.75
     на
    1.38
     Erkenntnis
    1.37
     через
    1.37
    LikeLiked
    1.34
    ergies
    1.33
    thirds
    1.31
    也算是
    1.30
    jsxFileName
    1.30
     в
    1.30
    Activations Density 0.008%

    No Known Activations