© 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. 111100
    Prev
    Next
    INDEX
    Explanations

    live broadcast announcements

    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
     for
    -0.79
     car
    -0.79
    踏
    -0.77
     SimpleName
    -0.76
    instagram
    -0.73
    中國
    -0.73
     Netflix
    -0.70
     by
    -0.70
    ธิ
    -0.70
    짜
    -0.69
    POSITIVE LOGITS
     radio
    1.38
    radio
    1.05
     RADIO
    1.04
     радио
    1.02
    RADIO
    1.00
     Radio
    1.00
    adio
    1.00
     akku
    0.95
     archived
    0.94
    Radio
    0.93
    Activations Density 0.061%

    No Known Activations