© 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. 22-GEMMASCOPE-RES-131K
    7. 27285
    Prev
    Next
    INDEX
    Explanations

    analog and traditional technology

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

    The neuron detects technical jargon—medium, mechanical, or instrumentation terms found in technical and engineering 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_22/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
     europa
    -1.02
    ULTS
    -1.01
    Const
    -0.98
     سازی
    -0.98
     courant
    -0.96
     kazi
    -0.96
     Travail
    -0.96
    obj
    -0.94
    hed
    -0.94
    ā
    -0.93
    POSITIVE LOGITS
     traditional
    1.67
     тради
    1.36
     traditionellen
    1.34
     klassischen
    1.30
    traditional
    1.28
     analog
    1.27
     analogue
    1.27
     tradizionale
    1.26
     tradicional
    1.22
     conventional
    1.21
    Activations Density 0.280%

    No Known Activations