© 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. 38223
    Prev
    Next
    INDEX
    Explanations

    DIY projects and tutorials

    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
     zostać
    -0.94
     baden
    -0.82
     padang
    -0.81
     новом
    -0.81
     surabaya
    -0.80
     centrally
    -0.80
     hemd
    -0.79
     折りたたみ
    -0.79
     仕事
    -0.79
    postolic
    -0.79
    POSITIVE LOGITS
     DIY
    4.03
    DIY
    3.23
     diy
    2.61
    diy
    2.31
     tutorial
    2.00
     homemade
    1.88
     tutorials
    1.84
     projects
    1.62
     crafts
    1.54
     easy
    1.49
    Activations Density 0.081%

    No Known Activations