© 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. 65706
    Prev
    Next
    INDEX
    Explanations

    onCreate savedInstanceState bundle

    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
     StringUtil
    -0.80
    ("~/
    -0.79
    BitConverter
    -0.79
     modules
    -0.77
     AssemblyVersion
    -0.76
    utí
    -0.76
    Dishwasher
    -0.72
    了呢
    -0.71
     AppDelegate
    -0.71
    FileStream
    -0.70
    POSITIVE LOGITS
    Resources
    1.14
     Resources
    1.13
    Bundle
    1.09
    final
    1.08
    Log
    1.06
     Bundle
    1.05
    Intent
    0.98
    View
    0.98
    Span
    0.98
     Intent
    0.93
    Activations Density 0.135%

    No Known Activations