© 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. 119061
    Prev
    Next
    INDEX
    Explanations

    webpack plugins and tools

    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
    جمه
    -0.77
    Poll
    -0.77
    DANCE
    -0.75
     Mors
    -0.74
    BigNumber
    -0.73
    jquery
    -0.73
    blas
    -0.72
    geer
    -0.72
     CRF
    -0.72
    уна
    -0.72
    POSITIVE LOGITS
     tool
    1.19
     tools
    1.18
     compiler
    1.13
     processing
    1.05
     build
    1.00
     tooling
    0.95
     compressor
    0.90
     preprocess
    0.89
    WebpackPlugin
    0.88
     preprocessing
    0.86
    Activations Density 0.177%

    No Known Activations