© 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. 92113
    Prev
    Next
    INDEX
    Explanations

    Jew, Israel, adoption

    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
     場所
    -0.77
    灝
    -0.76
    詛
    -0.76
    wirt
    -0.75
    protos
    -0.73
    שט
    -0.73
     ventilación
    -0.73
     Ради
    -0.73
    óz
    -0.72
    ってみた
    -0.72
    POSITIVE LOGITS
     absorption
    0.93
    absorption
    0.93
     ali
    0.90
    移民
    0.87
     علي
    0.87
     עלי
    0.79
     Absorption
    0.78
     facilitating
    0.77
     ignorance
    0.75
     absorbing
    0.75
    Activations Density 0.015%

    No Known Activations