© 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. 10-GEMMASCOPE-RES-131K
    7. 11889
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     so
    -0.99
     if
    -0.91
     as
    -0.91
     prescribed
    -0.89
    法官
    -0.88
    迦
    -0.87
    骄
    -0.85
     data
    -0.83
    ليز
    -0.83
     misión
    -0.82
    POSITIVE LOGITS
     همچنین
    1.08
     początku
    1.02
    ?」
    0.98
    everything
    0.97
    Essentially
    0.96
    newblock
    0.91
    essentially
    0.90
    Ранее
    0.90
    小心翼翼
    0.89
    stuff
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.