© 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. 102126
    Prev
    Next
    INDEX
    Explanations

    early or late in a phase

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

    The neuron fires on words that denote a temporal phase, period, or stage (e.g. “course,” “season,” “later,” “development,” “training”).

    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
     principalement
    -1.48
     VERY
    -1.42
    僦
    -1.41
     REALLY
    -1.39
     passado
    -1.38
    primarily
    -1.35
    THAT
    -1.34
    VERY
    -1.32
     continually
    -1.31
     probablement
    -1.31
    POSITIVE LOGITS
     when
    2.05
     it
    1.76
     where
    1.73
    when
    1.66
     during
    1.64
     two
    1.52
     these
    1.52
    värr
    1.45
     sebelum
    1.45
    istiwa
    1.44
    Activations Density 0.028%

    No Known Activations