© 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. 61174
    Prev
    Next
    INDEX
    Explanations

    memorable moments

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

    The neuron fires on words that highlight notable or peak events—terms like “moments,” “point,” “unforgettable,” “high point,” or “thrilling” that signal memorable or standout highlights.

    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
     who
    -1.74
     actualmente
    -1.73
     you
    -1.70
    <i>
    -1.67
     currently
    -1.63
    currently
    -1.61
    recently
    -1.55
     there
    -1.50
     atualmente
    -1.45
     récemment
    -1.45
    POSITIVE LOGITS
     moments
    1.49
     two
    1.39
     gave
    1.36
    setTotal
    1.33
     took
    1.31
     didalam
    1.29
    ಗಳ
    1.29
    +')
    1.26
     pape
    1.26
     jego
    1.26
    Activations Density 0.028%

    No Known Activations