© 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. 35003
    Prev
    Next
    INDEX
    Explanations

    the Simpsons characters

    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
    chaikovsky
    -0.87
     mineralization
    -0.84
    賃
    -0.83
    Scholar
    -0.81
     Scholar
    -0.75
    Parameteri
    -0.75
     McDonnell
    -0.71
    Reid
    -0.71
     Dulles
    -0.70
     cheetah
    -0.68
    POSITIVE LOGITS
     Simpsons
    2.02
     Springfield
    1.71
     Simpson
    1.71
     simpson
    1.62
     Homer
    1.60
    Simpson
    1.59
     Marge
    1.55
    Springfield
    1.55
    Homer
    1.48
     simpsons
    1.47
    Activations Density 0.018%

    No Known Activations