© 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. 84599
    Prev
    Next
    INDEX
    Explanations

    radical followed by concept

    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
    riae
    -0.87
    你想
    -0.86
     debacle
    -0.83
     resounding
    -0.82
     ravaged
    -0.81
    ywna
    -0.81
     trotzdem
    -0.80
    Caratteristiche
    -0.79
    
    -0.78
     Policía
    -0.78
    POSITIVE LOGITS
    ized
    1.29
     change
    1.27
     changes
    1.20
    isation
    1.14
     chic
    1.10
    ization
    1.06
     new
    0.98
    ويات
    0.96
     néz
    0.94
     changed
    0.93
    Activations Density 0.015%

    No Known Activations