© 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. 10-GEMMASCOPE-RES-131K
    7. 105776
    Prev
    Next
    INDEX
    Explanations

    window and following context

    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_10/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
    {
    -1.82
    .”
    -1.49
    }{
    -1.48
    bauten
    -1.46
    所有
    -1.44
    етесь
    -1.44
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.43
    cún
    -1.40
     ausencia
    -1.37
    𝑮
    -1.36
    POSITIVE LOGITS
     window
    2.06
     the
    2.02
    window
    1.90
     ventana
    1.79
     Window
    1.61
    self
    1.60
    1.59
     troubled
    1.57
     '
    1.55
     other
    1.55
    Activations Density 0.029%

    No Known Activations