© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66323
    Prev
    Next
    INDEX
    Explanations

    industrial and technological applications

    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
    TECHNOLOGY
    -1.26
     tecnología
    -1.23
     teknologi
    -1.19
    Technology
    -1.18
     TECHNOLOGY
    -1.15
     tecnologia
    -1.15
    technology
    -1.10
     technologie
    -1.09
    Technological
    -1.02
     Technologie
    -1.01
    POSITIVE LOGITS
     healthcare
    1.66
     medical
    1.63
     military
    1.55
     agriculture
    1.55
     surveillance
    1.52
     cities
    1.44
     medicine
    1.43
     security
    1.42
     monitoring
    1.40
     logistics
    1.38
    Activations Density 0.167%

    No Known Activations