© 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. 80867
    Prev
    Next
    INDEX
    Explanations

    foundation and basement protection

    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
    蹂
    -0.82
     SHOCK
    -0.79
    compound
    -0.72
     groote
    -0.72
     Carb
    -0.71
     balık
    -0.70
     cadastro
    -0.69
    orenje
    -0.68
     céré
    -0.68
     facteur
    -0.68
    POSITIVE LOGITS
     basement
    1.38
     waterproofing
    1.34
     foundation
    1.21
     Waterproof
    1.19
     Basement
    1.15
     crawl
    1.14
     Foundation
    1.12
     waterproof
    1.05
     sump
    1.04
    Foundation
    1.02
    Activations Density 0.005%

    No Known Activations