© 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. 39301
    Prev
    Next
    INDEX
    Explanations

    aceto or temporal markers

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

    This neuron detects sentence-initial temporal or discourse adverbs (“Antes,” “Prima,” “después,” etc.) that introduce a new clause.

    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
     for
    -2.61
     thier
    -2.55
    目前的
    -2.50
     them
    -2.42
    以前的
    -2.36
     locating
    -2.31
    ではまた
    -2.31
     barring
    -2.31
    iſter
    -2.17
    一定的
    -2.17
    POSITIVE LOGITS
    僦
    2.84
    The
    2.73
     chimique
    2.48
    鹇
    2.45
     که
    2.39
    硨
    2.36
    傒
    2.34
    ل
    2.31
    只有
    2.25
     lampada
    2.23
    Activations Density 0.001%

    No Known Activations