© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75110
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions

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

    The neuron activates on tokens that mark temporal sequencing or reference (e.g. words like “before,” “after,” “following,” “when,” etc.).

    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
     tirs
    -1.04
     échelle
    -1.02
     saks
    -1.02
     elef
    -1.01
     adornos
    -0.98
     asfalto
    -0.98
     adal
    -0.98
     detergente
    -0.97
     raso
    -0.96
     emporio
    -0.96
    POSITIVE LOGITS
     to
    2.28
     để
    1.31
    เพื่อ
    1.14
     Each
    1.02
     เพื่อ
    1.00
    centerTitle
    0.99
     +
    0.98
    struttura
    0.97
     terdapat
    0.96
     if
    0.95
    Activations Density 0.031%

    No Known Activations