© 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. 67734
    Prev
    Next
    INDEX
    Explanations

    connectors and lists

    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
    他们
    -1.66
     cuchara
    -1.55
    他們
    -1.51
     их
    -1.41
     вони
    -1.41
     loro
    -1.40
     mereka
    -1.38
     Mereka
    -1.36
     їх
    -1.31
    他们的
    -1.30
    POSITIVE LOGITS
     to
    2.14
     this
    1.82
    ～～～～
    1.41
     destacó
    1.41
     resistir
    1.37
    
    1.37
    dą
    1.36
    ⑼
    1.34
     電子
    1.32
     dikatakan
    1.29
    Activations Density 0.167%

    No Known Activations