© 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. 73453
    Prev
    Next
    INDEX
    Explanations

    corporate leadership roles

    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
    时长
    -0.80
     Annex
    -0.77
    peche
    -0.76
    spartner
    -0.76
     për
    -0.75
     cottura
    -0.74
     CLP
    -0.74
    versario
    -0.73
    hung
    -0.73
     Х
    -0.73
    POSITIVE LOGITS
     CEO
    2.20
    CEO
    1.87
     board
    1.48
     director
    1.45
     CEOs
    1.42
    ceo
    1.34
     agency
    1.29
     Director
    1.28
     directors
    1.20
     Geschäftsführer
    1.14
    Activations Density 0.022%

    No Known Activations