© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15300
    Prev
    Next
    INDEX
    Explanations

    days of establishment

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

    The neuron fires on numeric time‐limit expressions (e.g. “3 days of purchase,” “14 days of delivery,” “24 hours of …,” “9 days after …”), i.e. durations or deadlines.

    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
    嵛
    -1.34
    向了
    -1.34
    体は
    -1.14
    もともと
    -1.12
    ではまた
    -1.11
    打开了
    -1.10
    很多的
    -1.09
     aliento
    -1.09
    等は
    -1.09
     цвят
    -1.08
    POSITIVE LOGITS
     when
    1.32
     onset
    1.30
     start
    1.30
     시작
    1.23
     initial
    1.18
     which
    1.14
    เริ่ม
    1.13
     inception
    1.13
    開始
    1.11
     it
    1.09
    Activations Density 0.023%

    No Known Activations