© 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. 100369
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     they
    -1.50
     there
    -1.37
     betek
    -1.34
     功效
    -1.32
    middels
    -1.29
     the
    -1.27
     verdienen
    -1.27
     skrev
    -1.27
     gekocht
    -1.27
    și
    -1.26
    POSITIVE LOGITS
     BOTH
    1.87
    both
    1.78
     zarówno
    1.70
     และ
    1.58
     dogged
    1.57
     وفي
    1.56
    Both
    1.55
     tratados
    1.52
     mismas
    1.49
     reempla
    1.49
    Activations Density 0.050%

    No Known Activations