© 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. 90847
    Prev
    Next
    INDEX
    Explanations

    urls and database connections

    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
     enhancing
    -0.81
     enhance
    -0.81
     collaborative
    -0.78
     offered
    -0.77
     aspects
    -0.76
    ❈
    -0.75
     providing
    -0.75
     solely
    -0.75
     while
    -0.74
     enhances
    -0.74
    POSITIVE LOGITS
    http
    1.61
    https
    1.29
     http
    1.14
    mongodb
    1.02
    pherds
    0.95
    jdbc
    0.91
    wast
    0.89
     htt
    0.86
     https
    0.85
    alers
    0.84
    Activations Density 0.114%

    No Known Activations