© 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. 94177
    Prev
    Next
    INDEX
    Explanations

    Anno Domini, Hei, Huang

    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
    ESTON
    -0.88
     released
    -0.78
     أ
    -0.69
    class
    -0.68
     Edel
    -0.67
    فاف
    -0.65
     Lo
    -0.65
    เล
    -0.65
     Prieto
    -0.64
     haven
    -0.64
    POSITIVE LOGITS
    Era
    1.66
     Era
    1.61
     calendar
    1.55
     era
    1.50
     Anno
    1.38
     calendars
    1.31
    Calendar
    1.30
     Gregorian
    1.27
     Calendar
    1.20
    calendar
    1.14
    Activations Density 0.049%

    No Known Activations