© 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. 34-GEMMASCOPE-RES-131K
    7. 109471
    Prev
    Next
    INDEX
    Explanations

    competing or vying

    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_34/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
    젤
    -0.81
     シャンプー
    -0.79
    埂
    -0.75
     doce
    -0.75
    میز
    -0.75
    忑
    -0.73
    ţiei
    -0.72
    erade
    -0.72
    pair
    -0.71
    思议
    -0.71
    POSITIVE LOGITS
     vying
    3.00
     fight
    2.89
     competing
    2.72
    争
    2.72
     compete
    2.64
    爭
    2.59
     competes
    2.41
    fight
    2.34
     fighting
    2.28
     competed
    2.28
    Activations Density 0.064%

    No Known Activations