© 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. 10-GEMMASCOPE-RES-131K
    7. 47657
    Prev
    Next
    INDEX
    Explanations

    chewing gum, gum tree, gum disease

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to "gum" (whether chewing gum, tree gum, or gum tissue).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.92
    狨
    -2.83
    
    -2.81
    〠
    -2.73
    婳
    -2.73
    坶
    -2.66
     них
    -2.63
    鶿
    -2.63
    缡
    -2.61
    ჻
    -2.52
    POSITIVE LOGITS
    '
    2.75
    Surprisingly
    2.75
    釭
    2.55
    ;
    2.48
    「
    2.41
    Taking
    2.33
    ,…
    2.28
     groundbreaking
    2.25
    ,\\
    2.23
     conceptually
    2.23
    Activations Density 0.005%

    No Known Activations