© 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. 53950
    Prev
    Next
    INDEX
    Explanations

    errors and issues

    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
    entrepreneur
    -0.99
     doskon
    -0.96
     help
    -0.96
    缓解
    -0.96
     gesellschaft
    -0.94
    协助
    -0.93
    eniem
    -0.91
    astronomie
    -0.91
     Crown
    -0.91
    odils
    -0.90
    POSITIVE LOGITS
     lack
    1.23
    没有
    1.13
    这
    1.09
    ไม่
    1.05
     отсут
    1.03
    คุณ
    1.01
    問題
    1.00
     {//
    0.99
     الشاشة
    0.97
    Kenapa
    0.97
    Activations Density 0.028%

    No Known Activations