© 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. 25767
    Prev
    Next
    INDEX
    Explanations

    partition and historical events

    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
     κα
    -0.79
    ٻ
    -0.75
     הט
    -0.75
     hóa
    -0.74
     kê
    -0.73
     skid
    -0.72
    UTR
    -0.71
    遅い
    -0.71
     exposures
    -0.71
     Federal
    -0.71
    POSITIVE LOGITS
     Partition
    1.98
     partition
    1.84
    Partition
    1.73
    partition
    1.38
     partitioned
    1.37
     partitioning
    1.35
    PARTITION
    1.23
     تقسیم
    1.20
     partitions
    1.14
     विभ
    1.10
    Activations Density 0.013%

    No Known Activations