© 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. 86858
    Prev
    Next
    INDEX
    Explanations

    technical aspects and details

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

    The neuron activates on occurrences of the word “technical” (and closely associated terms like “review” or “details”) in context of technical reviews or specifications.

    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
    '
    -1.72
      
    -1.54
    致力于
    -1.48
    嗚
    -1.48
     So
    -1.47
    hacer
    -1.43
    调查
    -1.41
    蛤
    -1.41
    说到
    -1.39
    咳
    -1.39
    POSITIVE LOGITS
    technical
    2.19
     technical
    2.06
    慥
    2.05
    蚴
    1.95
     teknis
    1.84
    S
    1.77
     acuerdos
    1.74
     tecnica
    1.73
     Technical
    1.72
    year
    1.70
    Activations Density 0.043%

    No Known Activations