© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65864
    Prev
    Next
    INDEX
    Explanations

    development or to develop

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

    The neuron detects occurrences of “develop” or “development” (and their equivalents in other languages and inflected forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    '
    -2.33
    閦
    -2.03
    iſter
    -1.99
    ⵌ
    -1.97
    餍
    -1.92
    /
    -1.92
    粄
    -1.88
    韡
    -1.85
    翆
    -1.85
     ſy
    -1.80
    POSITIVE LOGITS
        
    2.20
    You
    2.14
    In
    2.11
     так
    2.02
     könne
    1.98
                    
    1.97
    我們
    1.97
              
    1.95
     sassy
    1.92
         
    1.91
    Activations Density 0.014%

    No Known Activations