© 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. 68810
    Prev
    Next
    INDEX
    Explanations

    death and casualty counts

    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
     {
    -1.76
    」
    -1.70
    </h3>
    -1.68
    <strong>
    -1.63
    。
    -1.61
    f
    -1.50
     realizadas
    -1.49
     if
    -1.48
     и
    -1.46
     .
    -1.45
    POSITIVE LOGITS
     trouw
    1.60
     resté
    1.52
    ようですが
    1.49
    ﮯ
    1.45
    籏
    1.38
     slechts
    1.35
     аппети
    1.34
    身后的
    1.34
     uyt
    1.33
     giày
    1.30
    Activations Density 0.025%

    No Known Activations