© 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. 61238
    Prev
    Next
    INDEX
    Explanations

    event duration

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

    The neuron fires on expressions denoting time durations (e.g. “week‐long,” “three-month ,” “long ”).

    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
    }
    -1.77
    也得
    -1.58
     \&
    -1.45
    </strong>
    -1.43
     douze
    -1.40
     watchful
    -1.38
     店内
    -1.38
     quatre
    -1.38
    的時候
    -1.37
    2
    -1.35
    POSITIVE LOGITS
     it
    1.34
    udert
    1.29
    讴
    1.28
     obviamente
    1.27
     defire
    1.26
    
    1.25
     wich
    1.21
     Monfieur
    1.21
     probablemente
    1.20
     piec
    1.20
    Activations Density 0.058%

    No Known Activations