© 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. 25854
    Prev
    Next
    INDEX
    Explanations

    Arab world, spring, revolt, conflict

    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
    绛
    -0.81
     actuator
    -0.80
    わせて
    -0.79
    Collegamenti
    -0.79
    Література
    -0.77
    ficar
    -0.77
    infra
    -0.76
    edata
    -0.76
    odyne
    -0.75
    اضر
    -0.75
    POSITIVE LOGITS
    ica
    0.90
    hama
    0.87
    arı
    0.84
     تاثیر
    0.84
    ilmente
    0.83
    △
    0.81
    Arab
    0.80
    ICA
    0.80
    League
    0.80
     League
    0.80
    Activations Density 0.008%

    No Known Activations