© 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. 4081
    Prev
    Next
    INDEX
    Explanations

    God, Lord, Creator titles

    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
    rader
    -0.95
     Христо
    -0.86
    ślę
    -0.84
     Divine
    -0.80
     Akin
    -0.79
    amentlich
    -0.79
    Divine
    -0.78
    神の
    -0.77
    broadcast
    -0.77
     disciple
    -0.76
    POSITIVE LOGITS
     who
    1.40
     creator
    1.19
     provider
    1.16
     maker
    1.07
    creator
    1.00
    Созда
    0.96
     living
    0.92
     Creator
    0.89
     alive
    0.88
     únicos
    0.87
    Activations Density 0.012%

    No Known Activations