© 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. 99441
    Prev
    Next
    INDEX
    Explanations

    mixing, kneading, and agitating

    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
     to
    -1.64
     verschied
    -1.63
    “
    -1.51
    izzato
    -1.48
     that
    -1.47
     verschiedene
    -1.45
    
    -1.45
     verschillende
    -1.43
    [
    -1.42
    es
    -1.40
    POSITIVE LOGITS
      
    1.56
     it
    1.55
     Two
    1.55
     our
    1.48
    engkapnya
    1.35
    
    1.29
     dirait
    1.26
    ubahan
    1.25
     Three
    1.24
     száz
    1.23
    Activations Density 0.057%

    No Known Activations