© 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. 25996
    Prev
    Next
    INDEX
    Explanations

    failed to open stream

    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
     breakthroughs
    -0.86
    ”？
    -0.81
     länge
    -0.81
     lilla
    -0.80
     {
    -0.80
    rooted
    -0.80
     Arxivat
    -0.79
    >+</
    -0.79
     francisco
    -0.78
    ？！”
    -0.77
    POSITIVE LOGITS
     geprüft
    0.97
     referência
    0.92
     cứu
    0.91
     fremden
    0.91
    BindingResult
    0.88
     everything
    0.86
    chiere
    0.86
     zukünf
    0.85
    উ
    0.84
    链
    0.84
    Activations Density 0.001%

    No Known Activations