© 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. 34-GEMMASCOPE-RES-131K
    7. 92974
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and blockchain

    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
     tecnología
    -1.07
     technolog
    -0.96
    Technology
    -0.96
     الرياض
    -0.92
     tecnologia
    -0.91
    🇴
    -0.89
     Technolog
    -0.87
     Euró
    -0.87
     terlaris
    -0.86
     технологи
    -0.84
    POSITIVE LOGITS
     cloud
    2.28
    cloud
    1.88
     Cloud
    1.70
     artificial
    1.66
     Artificial
    1.63
     AI
    1.54
     blockchain
    1.51
    Cloud
    1.43
     mobile
    1.39
     robotics
    1.35
    Activations Density 0.065%

    No Known Activations