© 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. 33576
    Prev
    Next
    INDEX
    Explanations

    at that time

    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
     this
    -1.14
     sesu
    -1.04
     berle
    -1.03
     sedia
    -0.96
     botol
    -0.94
    زون
    -0.93
     gaun
    -0.93
    NTT
    -0.92
     duk
    -0.88
     jari
    -0.88
    POSITIVE LOGITS
     time
    2.33
     period
    1.64
    time
    1.35
     временем
    1.27
     времени
    1.27
     época
    1.24
     czasu
    1.23
     الوقت
    1.17
     same
    1.16
     czasie
    1.16
    Activations Density 0.016%

    No Known Activations