© 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. 92261
    Prev
    Next
    INDEX
    Explanations

    training and workshops

    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
    ないです
    -0.98
     mengumumkan
    -0.92
     offerings
    -0.91
     друзей
    -0.88
     تحقی
    -0.87
    nacht
    -0.86
    服用
    -0.85
     исследований
    -0.84
     lingkungan
    -0.83
    ὴν
    -0.83
    POSITIVE LOGITS
     training
    2.45
     trainer
    1.94
     workshop
    1.85
     participants
    1.84
     trainers
    1.81
     Training
    1.72
     trainings
    1.70
     Trainer
    1.66
    Trainer
    1.64
    training
    1.55
    Activations Density 0.006%

    No Known Activations