© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33681
    Prev
    Next
    INDEX
    Explanations

    physical properties 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_34/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
     terça
    -1.00
     famí
    -0.96
     després
    -0.87
    waterproof
    -0.87
    を取る
    -0.86
    rhy
    -0.82
     negativos
    -0.81
     Samstag
    -0.80
    のですね
    -0.80
    躊
    -0.79
    POSITIVE LOGITS
     technology
    1.68
     material
    1.50
     materials
    1.46
     coating
    1.45
    Technology
    1.29
     devices
    1.27
    technology
    1.23
     coatings
    1.23
     properties
    1.23
     paint
    1.22
    Activations Density 0.138%

    No Known Activations