© 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. 81420
    Prev
    Next
    INDEX
    Explanations

    academic majors and degrees

    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
     Universitario
    -0.92
     decades
    -0.81
     regina
    -0.80
     décadas
    -0.79
     Trib
    -0.79
     derr
    -0.79
     retry
    -0.79
     when
    -0.79
    NSDate
    -0.78
     seder
    -0.77
    POSITIVE LOGITS
    double
    1.03
     double
    0.98
     technische
    0.94
     Global
    0.94
     estudar
    0.93
     technisch
    0.91
     Honors
    0.90
     biomedical
    0.88
     Biomedical
    0.88
     bio
    0.85
    Activations Density 0.037%

    No Known Activations