© 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. 116846
    Prev
    Next
    INDEX
    Explanations

    financial reductions and deductions

    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
    лыша
    -0.81
    倶楽部
    -0.77
     Fee
    -0.76
     протя
    -0.75
    Fees
    -0.75
    щений
    -0.74
     Uniwersyte
    -0.74
    fees
    -0.73
    velser
    -0.73
     fee
    -0.73
    POSITIVE LOGITS
     reduction
    2.28
    Reduce
    2.17
     reduce
    2.17
    reduce
    2.11
     Reduce
    2.03
     reductions
    1.98
     reducing
    1.95
     reduced
    1.93
     offset
    1.89
     reduces
    1.89
    Activations Density 0.023%

    No Known Activations