© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43280
    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
    ↵↵
    -1.80
    </u>
    -1.43
     säl
    -1.34
    premiere
    -1.31
    paisaje
    -1.28
    {
    -1.28
    
    -1.24
     pè
    -1.21
    modellen
    -1.21
     fråga
    -1.20
    POSITIVE LOGITS
    that
    1.27
     dismiss
    1.21
    Πηγές
    1.16
    an
    1.11
     fulf
    1.10
     заключается
    1.10
     efferves
    1.10
    zeera
    1.09
     тща
    1.09
    x
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.