© 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. 40930
    Prev
    Next
    INDEX
    Explanations

    mechanical and electrical engineering

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

    The main thing this neuron does is detect mentions of engineering disciplines (e.g., mechanical engineering, electrical engineering, civil engineering, etc.).

    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
    They
    -1.60
     thru
    -1.59
    ,”
    -1.44
     ‘
    -1.42
     undeniable
    -1.41
    ....
    -1.39
    .....
    -1.39
    …
    -1.34
    s
    -1.34
    es
    -1.34
    POSITIVE LOGITS
     ventilación
    1.67
    ться
    1.54
     estabilidad
    1.48
     tracción
    1.47
     productividad
    1.46
    棡
    1.45
     personalización
    1.45
     maquinaria
    1.44
     importación
    1.43
     lavadora
    1.42
    Activations Density 0.032%

    No Known Activations