© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3438
    Prev
    Next
    INDEX
    Explanations

    missionary or missions

    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
    Negative Logits
     buffet
    -0.81
    OfYear
    -0.78
    ("}\
    -0.76
     consultato
    -0.74
     Tuf
    -0.73
    XIV
    -0.71
     år
    -0.71
    具
    -0.71
    Año
    -0.69
     valuations
    -0.69
    POSITIVE LOGITS
     missionary
    1.78
     mission
    1.68
     missions
    1.52
     missionaries
    1.52
    Mission
    1.50
    mission
    1.43
     Mission
    1.43
     Missionary
    1.38
     Missions
    1.30
    missions
    1.25
    Activations Density 0.014%

    No Known Activations