© 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. 10-GEMMASCOPE-RES-131K
    7. 19680
    Prev
    Next
    INDEX
    Explanations

    forward, backward, rewind, advance

    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_10/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
    S
    -2.02
    ↵↵
    -1.91
     MUCH
    -1.85
    {
    -1.73
     new
    -1.73
    replyreport
    -1.70
     benötigt
    -1.66
     khi
    -1.65
     you
    -1.64
     nuevos
    -1.60
    POSITIVE LOGITS
     teď
    1.96
     ſou
    1.88
    沵
    1.83
     唯美
    1.83
    闼
    1.81
    嗵
    1.80
    鸝
    1.78
     cinqu
    1.77
    𓆏
    1.76
    煳
    1.74
    Activations Density 0.004%

    No Known Activations