© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54063
    Prev
    Next
    INDEX
    Explanations

    weight or burden

    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
     времена
    -0.73
     stellt
    -0.72
     Embedded
    -0.72
    ummies
    -0.72
    uerre
    -0.71
    rosophila
    -0.71
    outons
    -0.71
    жні
    -0.70
    ختلف
    -0.70
    vanni
    -0.70
    POSITIVE LOGITS
     burden
    4.13
     burdens
    3.38
    burden
    3.31
     Burden
    3.03
     weight
    2.75
     burdened
    2.55
     load
    2.55
     weights
    2.39
     weighs
    2.36
    weight
    2.34
    Activations Density 0.039%

    No Known Activations