© 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. 55913
    Prev
    Next
    INDEX
    Explanations

    Q: questions and statements

    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
     battery
    -0.82
     goal
    -0.78
     bathing
    -0.78
    Damp
    -0.77
    ieden
    -0.75
    ίδ
    -0.75
     хотел
    -0.75
     spir
    -0.74
     wier
    -0.74
     forehead
    -0.73
    POSITIVE LOGITS
    コロナ
    0.90
    ROOM
    0.88
    켜
    0.85
     режим
    0.82
     nejlepší
    0.81
    
    0.79
    聾
    0.79
    says
    0.78
    我们
    0.78
    Miami
    0.77
    Activations Density 0.012%

    No Known Activations