© 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. 7317
    Prev
    Next
    INDEX
    Explanations

    author and metadata in comments

    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
     %{
    -0.84
     deň
    -0.84
     veľ
    -0.82
    骶
    -0.81
     város
    -0.81
    helen
    -0.80
     密码
    -0.80
     nového
    -0.79
     库存
    -0.78
    mijn
    -0.78
    POSITIVE LOGITS
     author
    2.48
     Author
    2.13
     authors
    2.00
    author
    1.95
    Author
    1.91
     authored
    1.91
     date
    1.84
     written
    1.74
     Date
    1.64
    date
    1.55
    Activations Density 0.196%

    No Known Activations