© 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. 60580
    Prev
    Next
    INDEX
    Explanations

    interfering with governmental or any right

    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
     each
    -1.07
     everything
    -1.00
     sometimes
    -0.95
     tava
    -0.94
     every
    -0.92
     teka
    -0.91
     випад
    -0.88
     everywhere
    -0.87
     murm
    -0.87
    Each
    -0.85
    POSITIVE LOGITS
     किसी
    1.03
     MATTERS
    1.00
    arschu
    0.96
     pending
    0.94
     gustó
    0.94
    inflater
    0.93
    侖
    0.90
     asuntos
    0.88
     official
    0.86
     ഒരു
    0.85
    Activations Density 0.024%

    No Known Activations