© 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. 70163
    Prev
    Next
    INDEX
    Explanations

    long duration lifetime

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

    The neuron fires on the adjective “long” when it appears as part of hyphenated or compound modifiers (e.g. long-lasting, long-range, long-running) indicating extended duration or extent.

    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
    
    -0.77
    ctan
    -0.70
     rage
    -0.69
     हा
    -0.69
     değiştir
    -0.68
    ondra
    -0.68
    
    -0.66
     ξ
    -0.65
     высокого
    -0.65
     rush
    -0.65
    POSITIVE LOGITS
    spring
    0.83
    ByExample
    0.81
    itzende
    0.75
    long
    0.75
     archivi
    0.73
    Settings
    0.71
     afili
    0.71
    ——”
    0.70
    );//
    0.70
    verne
    0.70
    Activations Density 0.030%

    No Known Activations