© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8052
    Prev
    Next
    INDEX
    Explanations

    element list representation

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

    The neuron fires on the term “element” (and its plural “elements”) in technical or code contexts.

    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
    ,”
    -2.03
    ”？
    -1.95
    ’
    -1.91
     myſelf
    -1.70
    有
    -1.62
     fossero
    -1.61
    那些
    -1.59
     itſelf
    -1.51
     facendo
    -1.50
    全都
    -1.48
    POSITIVE LOGITS
    
    2.50
    翆
    2.48
    𖥧
    2.30
    萑
    2.30
     podem
    2.20
    䜣
    1.98
    汌
    1.98
    珦
    1.96
    朏
    1.93
    沄
    1.92
    Activations Density 0.033%

    No Known Activations