© 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. 10-GEMMASCOPE-RES-131K
    4. 80739
    Prev
    Next
    INDEX
    Explanations

    past followed by time duration

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

    The neuron detects mentions of multi‐unit time spans, especially phrases like “for the past ___ years/weeks.”

    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
    品の
    -1.48
     componentes
    -1.45
    stunden
    -1.44
    spodnie
    -1.44
     münchen
    -1.44
     producen
    -1.44
     HttpNotFound
    -1.41
     gardent
    -1.40
     barva
    -1.38
    izando
    -1.37
    POSITIVE LOGITS
    '
    1.82
    O
    1.62
     angesehen
    1.62
    2
    1.55
    iti
    1.54
    5
    1.53
    -
    1.52
    ;
    
    1.52
    мышлен
    1.45
    S
    1.44
    Activations Density 0.013%

    No Known Activations