© 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. 99740
    Prev
    Next
    INDEX
    Explanations

    it is time to

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

    This neuron primarily detects occurrences of the word “time” (especially in phrases like “it’s time to…” or “time we…”).

    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
     one
    -1.70
     first
    -1.64
     your
    -1.64
     on
    -1.60
     may
    -1.60
     meticulous
    -1.59
    鸰
    -1.55
     reinforce
    -1.53
     optimal
    -1.52
     maintain
    -1.51
    POSITIVE LOGITS
     eſſ
    1.98
     citroen
    1.91
    
    1.78
     monaster
    1.76
     kano
    1.70
    糁
    1.70
     yako
    1.69
    盌
    1.69
     incess
    1.68
     Igles
    1.67
    Activations Density 0.006%

    No Known Activations