© 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. 111031
    Prev
    Next
    INDEX
    Explanations

    publication date and time

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

    The neuron detects date and time metadata (timestamps like “Posted Oct 19, 2021 at 12:01 AM” and “Updated Oct 19, 2021 at 7:04 PM”).

    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
    dì
    -1.36
    🕗
    -1.33
     karakter
    -1.32
     wortel
    -1.32
    を感じる
    -1.31
     ผม
    -1.31
     bambú
    -1.31
    を感じ
    -1.30
     小物
    -1.30
    Lyric
    -1.29
    POSITIVE LOGITS
     then
    1.63
    //
    1.61
    mathrm
    1.48
    All
    1.45
    Then
    1.41
    D
    1.41
    self
    1.39
    i
    1.37
    ili
    1.34
    An
    1.33
    Activations Density 0.131%

    No Known Activations