© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129495
    Prev
    Next
    INDEX
    Explanations

    unincorporated community

    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
     سریال
    -0.99
     precin
    -0.96
     olor
    -0.96
     خریدار
    -0.94
    書籍
    -0.94
    んでも
    -0.93
     Zika
    -0.93
     增
    -0.92
    ってない
    -0.91
     pilla
    -0.91
    POSITIVE LOGITS
     Furthermore
    1.06
     químicas
    1.05
     and
    1.02
     ChatGPT
    1.00
    の詳細
    0.99
     Moreover
    0.98
    の概要
    0.97
     ElevatedButton
    0.96
    有很多
    0.96
     سرطان
    0.96
    Activations Density 0.003%

    No Known Activations