© 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. 7998
    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
    讠
    -2.81
    骈
    -2.69
    欉
    -2.59
    choso
    -2.53
     zwaar
    -2.52
    ?”
    -2.52
    愎
    -2.50
    鋌
    -2.50
    閂
    -2.48
     Ağustos
    -2.45
    POSITIVE LOGITS
     -
    3.17
    2
    2.78
    ing
    2.75
     {
    2.66
     \
    2.61
    翆
    2.59
     l
    2.50
    )
    2.50
    </strong>
    2.45
     /
    2.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.