© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    Donald Trump Kennedy

    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
     that
    -1.52
    șe
    -1.02
     करके
    -0.91
     lectores
    -0.90
    ที่จะ
    -0.88
     něj
    -0.87
    octanol
    -0.83
    쌀
    -0.82
    ském
    -0.82
     ellas
    -0.81
    POSITIVE LOGITS
     there
    1.01
    marcos
    0.90
     certain
    0.89
     convencer
    0.86
    fizz
    0.83
    空调
    0.81
     nimmer
    0.81
     bakso
    0.81
    roberto
    0.80
     discover
    0.80
    Activations Density 0.031%

    No Known Activations