© 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. 98080
    Prev
    Next
    INDEX
    Explanations

    God, creator, existence, Word

    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
     mär
    -0.83
     where
    -0.80
    awarkan
    -0.75
    ශ
    -0.72
    Seguir
    -0.71
    Տես
    -0.70
    ડ
    -0.70
    tales
    -0.70
     du
    -0.69
     behaviors
    -0.69
    POSITIVE LOGITS
     existed
    1.24
     eternal
    1.00
     ewig
    0.94
     existent
    0.92
     eternally
    0.90
     Word
    0.88
     Exist
    0.88
    阂
    0.87
     creator
    0.86
     sustains
    0.86
    Activations Density 0.007%

    No Known Activations