© 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. 89819
    Prev
    Next
    INDEX
    Explanations

    Project Tango, Denver, Q, I

    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
    reactive
    -0.81
     Car
    -0.77
     ворота
    -0.76
    ὕ
    -0.76
    XMLHttpRequest
    -0.75
    льский
    -0.73
    导入
    -0.73
     Col
    -0.72
    äden
    -0.72
     Penelitian
    -0.72
    POSITIVE LOGITS
     comparing
    0.77
    ⊷
    0.76
     دیکھیے
    0.75
     splitter
    0.74
    xem
    0.74
     pagine
    0.73
     should
    0.73
     phases
    0.72
    riak
    0.72
     before
    0.71
    Activations Density 0.017%

    No Known Activations