© 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. 22-GEMMASCOPE-RES-131K
    7. 93098
    Prev
    Next
    INDEX
    Explanations

    bucket sizes or list lengths

    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_22/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
     varier
    -0.96
     איז
    -0.94
     seks
    -0.93
     новом
    -0.93
     kän
    -0.93
     nieuwe
    -0.92
     winkel
    -0.91
     تغيير
    -0.89
     navideño
    -0.89
    ondissement
    -0.87
    POSITIVE LOGITS
    最初
    0.99
    或
    0.94
    途中
    0.90
     maybe
    0.90
     expertly
    0.89
    andingan
    0.89
    未
    0.88
     to
    0.87
     masses
    0.85
    英雄
    0.85
    Activations Density 0.057%

    No Known Activations