© 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. 34-GEMMASCOPE-RES-131K
    7. 60909
    Prev
    Next
    INDEX
    Explanations

    time has flown

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

    The neuron activates strongly on words and phrases that refer to the passage of time—months, seasons, years, and time‐progression verbs (e.g. “flown,” “flying,” “year,” “August”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Boh
    -0.79
    ↱
    -0.77
    Fj
    -0.71
     willkommen
    -0.69
     Boh
    -0.69
    turma
    -0.69
     pesquisa
    -0.68
    ທ
    -0.67
     Méditerranée
    -0.67
     nacimiento
    -0.67
    POSITIVE LOGITS
     fly
    4.81
     flew
    4.28
     flying
    4.25
     flies
    3.84
    fly
    3.61
     FLY
    3.52
    FLY
    3.44
    Fly
    3.41
    flying
    3.30
     Fly
    3.28
    Activations Density 0.053%

    No Known Activations