© 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. 82647
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and tasks

    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
     pajama
    -0.93
    histle
    -0.76
    şehir
    -0.76
    اف
    -0.75
    DataSnapshot
    -0.75
    穂
    -0.74
    Ӯ
    -0.73
    ƙ
    -0.72
     Adjusting
    -0.71
    stram
    -0.71
    POSITIVE LOGITS
     multiplication
    2.89
     addition
    2.77
     arithmetic
    2.59
     division
    2.50
     subtraction
    2.42
     Addition
    2.39
     operations
    2.27
    addition
    2.23
    division
    2.22
    Addition
    2.17
    Activations Density 0.162%

    No Known Activations