© 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. 81519
    Prev
    Next
    INDEX
    Explanations

    discoveries and exploration

    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
     thank
    -0.90
    mobile
    -0.87
     Mobile
    -0.85
     mobile
    -0.84
    携帯
    -0.81
    オーナー
    -0.80
    libft
    -0.78
     because
    -0.75
     when
    -0.75
    othea
    -0.75
    POSITIVE LOGITS
    discover
    1.45
    Discover
    1.34
    Explore
    1.29
     Discover
    1.15
    explore
    1.10
     discoveries
    1.08
     discover
    1.04
     discovery
    1.01
    search
    1.00
    Profile
    0.98
    Activations Density 0.012%

    No Known Activations