© 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. 130719
    Prev
    Next
    INDEX
    Explanations

    cap or capping

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

    The neuron activates for the word "capped" and related forms like "cap", particularly when referring to covering or topping something.

    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
    ↵↵
    -2.77
    .
    -2.73
     verbess
    -2.42
    {
    -2.39
     to
    -1.98
    vernote
    -1.80
    ']>
    -1.73
    梛
    -1.73
    
    -1.72
    $:
    -1.70
    POSITIVE LOGITS
    Fär
    2.02
    d
    1.99
    kwür
    1.93
    All
    1.92
    
    1.89
    最初の
    1.87
    i
    1.87
    Several
    1.86
    Other
    1.85
     området
    1.85
    Activations Density 0.011%

    No Known Activations