© 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. 75273
    Prev
    Next
    INDEX
    Explanations

    political, economic, industry, activist, policy

    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
    了一些
    -1.67
     liés
    -1.61
     stále
    -1.50
    了自己的
    -1.49
     '
    -1.48
     nová
    -1.47
     большого
    -1.37
    的方式
    -1.36
    refront
    -1.35
    寂寞
    -1.34
    POSITIVE LOGITS
     aben
    2.03
     anun
    2.00
     megane
    1.76
     ヶ
    1.73
     noss
    1.71
     vost
    1.70
     limita
    1.69
     noft
    1.66
     Igles
    1.59
     papan
    1.59
    Activations Density 24.054%

    No Known Activations