© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59545
    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
     tevreden
    -1.05
    什么意思
    -1.05
    -1.03
    יפור
    -1.00
    一样的
    -0.99
    ícias
    -0.99
    利
    -0.98
    无关
    -0.97
     gemaakt
    -0.97
    その時
    -0.97
    POSITIVE LOGITS
    甚至
    1.09
    或
    1.00
    ９
    0.98
    <blockquote>
    0.96
     econó
    0.94
     множество
    0.93
    卖家
    0.91
    و
    0.90
    THE
    0.90
     [
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.