© 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. 105692
    Prev
    Next
    INDEX
    Explanations

    ado words

    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
     It
    -2.83
    ឵
    -2.78
    ⚋
    -2.70
    vantaged
    -2.66
    戬
    -2.63
    屄
    -2.48
    起床
    -2.48
    稣
    -2.45
    伥
    -2.45
    逡
    -2.44
    POSITIVE LOGITS
     They
    2.61
    that
    2.48
    ↵
    2.48
    {
    2.23
    戏剧
    2.20
    <i>
    2.08
    Y
    2.06
     it
    2.03
    讽
    2.02
    你在
    1.98
    Activations Density 0.001%

    No Known Activations