© 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. 12557
    Prev
    Next
    INDEX
    Explanations

    mnemonic heuristic phonetic

    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
    d
    -2.78
    函館
    -2.06
     {
    -1.98
    ↵
    -1.89
    现在的
    -1.87
     With
    -1.80
     nahezu
    -1.75
    خبر
    -1.72
    日本的
    -1.71
     When
    -1.70
    POSITIVE LOGITS
    
    2.34
    盞
    2.27
    年
    1.87
    塒
    1.84
    琛
    1.83
    ())));
    1.80
    curity
    1.80
    bustible
    1.77
    
    1.77
    ၌
    1.74
    Activations Density 0.005%

    No Known Activations