© 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. 84740
    Prev
    Next
    INDEX
    Explanations

    loss, mean, sum, averaged

    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
     temor
    -0.86
     récompense
    -0.86
     هنری
    -0.82
     Internazionale
    -0.82
     Ahmedabad
    -0.82
     descente
    -0.80
    ↓↓
    -0.79
     snipers
    -0.78
     นิ้ว
    -0.78
    akuza
    -0.78
    POSITIVE LOGITS
     Loss
    1.21
     losses
    1.13
     loss
    1.11
     mean
    1.01
     Mean
    0.98
     sum
    0.98
    Loss
    0.98
     averaged
    0.96
    챙
    0.93
    loss
    0.91
    Activations Density 0.004%

    No Known Activations