© 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. 10-GEMMASCOPE-RES-131K
    4. 80668
    Prev
    Next
    INDEX
    Explanations

    java.lang.* and org.*

    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
     Those
    -2.30
     Both
    -2.03
     Of
    -1.90
     Each
    -1.83
    Both
    -1.72
    There
    -1.70
    Those
    -1.65
    "].
    -1.64
    ’.
    -1.63
     chaque
    -1.63
    POSITIVE LOGITS
     hvilke
    1.78
     suministro
    1.74
     sodio
    1.66
    <bos>
    1.65
     today
    1.61
     acabados
    1.59
     purported
    1.58
    linawan
    1.57
    푃
    1.55
     discussing
    1.54
    Activations Density 0.012%

    No Known Activations