© 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. 38042
    Prev
    Next
    INDEX
    Explanations

    character roles and names

    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
    一惊
    -0.95
    nf
    -0.91
    \}$,
    -0.90
    
    -0.90
     atriz
    -0.89
    setResizable
    -0.88
    ϳ
    -0.87
    втор
    -0.85
     He
    -0.84
     john
    -0.84
    POSITIVE LOGITS
     everyone
    1.13
     reduzir
    1.10
     everybody
    1.06
     ativar
    1.02
     equipamentos
    0.99
     fornecer
    0.98
     ajudar
    0.96
     apresentar
    0.95
     melhorar
    0.94
     equipamento
    0.94
    Activations Density 0.031%

    No Known Activations