© 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. 14169
    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
     then
    -1.85
     Ergänzung
    -1.55
     This
    -1.54
    .
    -1.45
     Once
    -1.41
     adding
    -1.34
    最初
    -1.33
     Initially
    -1.33
     gently
    -1.32
     плохо
    -1.30
    POSITIVE LOGITS
     vokal
    1.45
    Aristotle
    1.45
     pria
    1.43
     unut
    1.43
    ſelf
    1.42
     maksi
    1.40
    /**/*.
    1.38
     statut
    1.35
     parha
    1.34
     pü
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.