© 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. 75206
    Prev
    Next
    INDEX
    Explanations

    jupyter notebook setup

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

    The neuron detects mentions of Jupyter notebooks (e.g. the words “Jupyter” or “notebook”).

    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
     کیا
    -1.79
    缡
    -1.76
     наши
    -1.69
     disfraces
    -1.68
     mutta
    -1.68
     pracuje
    -1.66
    砗
    -1.66
     namun
    -1.66
    umą
    -1.66
     barvy
    -1.66
    POSITIVE LOGITS
     constituye
    1.71
    㐂
    1.66
     erläut
    1.63
    u
    1.63
     esencial
    1.57
     eradicate
    1.55
              
    1.55
        
    1.55
    ו
    1.55
     Basically
    1.52
    Activations Density 0.002%

    No Known Activations