© 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. 9259
    Prev
    Next
    INDEX
    Explanations

    political aide

    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
    鲠
    -2.64
    蹂
    -2.36
    s
    -2.36
    allible
    -2.31
     Kindern
    -2.31
     esteemed
    -2.25
    abatic
    -2.23
    嵛
    -2.23
    玙
    -2.22
    玏
    -2.22
    POSITIVE LOGITS
    ╂
    2.13
    和她
    2.09
     eşofman
    2.03
     demasiado
    1.97
    先后
    1.95
    ing
    1.92
    льность
    1.90
    十分钟
    1.90
     допомогти
    1.86
     Meksika
    1.86
    Activations Density 0.003%

    No Known Activations