© 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. 39537
    Prev
    Next
    INDEX
    Explanations

    dominance or provenance of names

    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
    ',
    -3.05
     {
    -2.92
    。“
    -2.52
    eração
    -2.50
    、“
    -2.50
     \
    -2.45
     You
    -2.42
    g
    -2.41
     verbeteren
    -2.41
     seems
    -2.38
    POSITIVE LOGITS
     แต่
    2.66
    屨
    2.55
     見える
    2.55
     rajut
    2.34
     menyen
    2.22
     gemis
    2.20
     شعار
    2.19
     グリル
    2.19
    Protecting
    2.17
     knapp
    2.16
    Activations Density 0.006%

    No Known Activations