© 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. 34902
    Prev
    Next
    INDEX
    Explanations

    source and binary forms

    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
     Radioactive
    -0.90
     blijkt
    -0.86
    🏯
    -0.82
    レンダー
    -0.81
     Keny
    -0.80
    몹
    -0.80
     seguía
    -0.80
     resurre
    -0.79
     hidratante
    -0.79
    tôi
    -0.78
    POSITIVE LOGITS
     electronic
    1.22
     storage
    1.14
     by
    1.07
     elektron
    1.07
    by
    1.05
     manual
    1.02
     stored
    1.02
    electronic
    1.00
     whether
    1.00
     mechanical
    0.99
    Activations Density 0.025%

    No Known Activations