© 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. 34-GEMMASCOPE-RES-131K
    7. 63037
    Prev
    Next
    INDEX
    Explanations

    products, solutions, and equipment

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

    This neuron activates on mentions of specific industrial or technical products, components, or equipment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     when
    -2.05
     or
    -1.93
     after
    -1.91
     because
    -1.70
     this
    -1.67
     if
    -1.63
     before
    -1.63
     during
    -1.60
     three
    -1.52
     five
    -1.51
    POSITIVE LOGITS
    primarily
    2.17
    mainly
    1.98
    particularly
    1.80
     rése
    1.76
    mostly
    1.67
     rigide
    1.54
     geene
    1.54
     vitale
    1.54
     principalement
    1.50
    omorphisms
    1.50
    Activations Density 0.120%

    No Known Activations