© 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. 87184
    Prev
    Next
    INDEX
    Explanations

    macOS related software and utilities

    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
    インテリア
    -0.80
    騨
    -0.77
    沸
    -0.73
    gett
    -0.71
    yden
    -0.69
     Ecol
    -0.69
    phology
    -0.68
     compositor
    -0.67
     Nass
    -0.66
     Html
    -0.66
    POSITIVE LOGITS
     parallels
    1.11
     Paralle
    1.02
     parallel
    0.85
     Parallel
    0.85
     Front
    0.79
    paralle
    0.78
    Parallel
    0.74
    parallel
    0.73
     Duncan
    0.73
     paralle
    0.73
    Activations Density 0.073%

    No Known Activations