© 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. 118323
    Prev
    Next
    INDEX
    Explanations

    stephen hawking

    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
    烹
    -0.74
     عبدالله
    -0.69
     mentoring
    -0.69
     wakati
    -0.69
    Nied
    -0.69
     Rectangle
    -0.69
     منت
    -0.68
     Sentinel
    -0.67
    anello
    -0.66
     biel
    -0.65
    POSITIVE LOGITS
     Hawking
    1.91
     Stephen
    1.39
    Stephen
    1.24
     stephen
    1.02
     cosmology
    1.02
     Hawk
    1.02
    Haw
    0.97
     STEPHEN
    0.94
    hawk
    0.94
     cosmo
    0.93
    Activations Density 0.029%

    No Known Activations