© 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. 67494
    Prev
    Next
    INDEX
    Explanations

    physics and science terms

    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
     dedica
    -1.43
     السياس
    -1.41
     δὲ
    -1.39
    crollView
    -1.35
     její
    -1.34
     النبات
    -1.34
     itself
    -1.32
     meteen
    -1.30
     its
    -1.29
    Its
    -1.27
    POSITIVE LOGITS
     all
    1.78
     those
    1.56
     these
    1.52
     fometimes
    1.44
     unggul
    1.42
    久しぶりに
    1.41
    景象
    1.37
     оружи
    1.34
     different
    1.34
     you
    1.32
    Activations Density 0.096%

    No Known Activations