© 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. 66262
    Prev
    Next
    INDEX
    Explanations

    programs and policies

    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
     способов
    -1.05
    
    -1.00
    DeleteMapping
    -1.00
     trastornos
    -0.94
    ỗi
    -0.94
    あー
    -0.92
    小小的
    -0.91
     nama
    -0.89
     Mut
    -0.89
    ChangeListener
    -0.88
    POSITIVE LOGITS
     activities
    1.17
     activity
    1.16
     decisions
    0.97
     effort
    0.94
     efforts
    0.94
    がありますが
    0.94
     in
    0.93
    实践
    0.90
     practice
    0.89
    鯛
    0.89
    Activations Density 0.164%

    No Known Activations