© 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. 33172
    Prev
    Next
    INDEX
    Explanations

    political peace agreements

    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
     संस्
    -0.85
     الرحمن
    -0.80
     HMRC
    -0.77
     gyro
    -0.77
     Hispanic
    -0.75
     Giud
    -0.74
     contractor
    -0.73
     prosecuting
    -0.73
     demolition
    -0.72
    用法
    -0.72
    POSITIVE LOGITS
    agreement
    1.04
    agree
    1.01
    inclu
    1.00
     agreement
    0.98
     maisons
    0.98
     Agreement
    0.95
    agreed
    0.91
     Inclu
    0.91
     peace
    0.90
    peace
    0.90
    Activations Density 0.011%

    No Known Activations