© 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. 22-GEMMASCOPE-RES-131K
    7. 36347
    Prev
    Next
    INDEX
    Explanations

    compound words and specific suffixes;

    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_22/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
     then
    -0.95
    kových
    -0.91
    えると
    -0.91
    bürgermeister
    -0.87
    اما
    -0.87
    jadikan
    -0.83
    manız
    -0.83
    tingham
    -0.83
     erfolgreichen
    -0.83
     THEN
    -0.82
    POSITIVE LOGITS
     ся
    0.91
    全体
    0.84
    氧化
    0.83
    alogy
    0.81
     title
    0.81
    命令
    0.80
    Filing
    0.80
     架
    0.80
    只好
    0.78
    洗手
    0.78
    Activations Density 0.008%

    No Known Activations