© 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. 8722
    Prev
    Next
    INDEX
    Explanations

    technology and technique

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

    The neuron fires on the word “technology” (and its close variants) whenever it appears in the text.

    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
     recommandations
    -1.79
     dévelo
    -1.74
    取り組み
    -1.73
     intrinsically
    -1.70
    鲀
    -1.69
    舸
    -1.69
    瓛
    -1.69
     maleta
    -1.67
     exercices
    -1.65
    亮点
    -1.63
    POSITIVE LOGITS
     to
    3.05
    </em>
    2.19
    ”.
    2.13
     Können
    2.02
    ”,
    1.97
    </h4>
    1.93
     zumal
    1.92
    D
    1.90
    良い
    1.87
     täglichen
    1.85
    Activations Density 0.020%

    No Known Activations