© 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. 7922
    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
    </h1>
    -1.56
    )=>{
    -1.30
    ↵↵
    -1.28
     verschiedenen
    -1.26
     by
    -1.23
     świecie
    -1.23
     unmittelbar
    -1.20
     bestimm
    -1.19
    ดด
    -1.16
    s
    -1.15
    POSITIVE LOGITS
     cewek
    1.47
    gezogen
    1.43
     achet
    1.41
     ratón
    1.41
    unser
    1.37
    getting
    1.34
     parachoque
    1.34
    ístico
    1.34
    Kirchen
    1.32
     Plane
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.