© 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. 9703
    Prev
    Next
    INDEX
    Explanations

    deformation of materials

    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
     
    -3.06
    ↵↵
    -2.72
    焄
    -2.67
    IN
    -2.61
    ’
    -2.58
     I
    -2.44
    ⩴
    -2.39
      
    -2.28
     nimmer
    -2.27
     ABOUT
    -2.25
    POSITIVE LOGITS
    。“
    2.66
    、“
    2.59
     sposób
    2.39
    捭
    2.31
     longstanding
    2.31
     اكتوبر
    2.28
    矯
    2.27
    结语
    2.25
    嵛
    2.23
    ábado
    2.22
    Activations Density 0.003%

    No Known Activations