© 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. 60849
    Prev
    Next
    INDEX
    Explanations

    time and duration in the future

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     lately
    -0.90
    当時
    -0.90
     depuis
    -0.88
    也能
    -0.88
     登
    -0.87
     lemn
    -0.86
     recently
    -0.83
    尝试
    -0.82
     previously
    -0.82
    短短
    -0.82
    POSITIVE LOGITS
     years
    2.45
     months
    1.85
     several
    1.85
     YEARS
    1.79
    years
    1.59
    อีก
    1.58
     another
    1.57
     decades
    1.55
    Several
    1.54
    至少
    1.53
    Activations Density 0.023%

    No Known Activations