© 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. 10-GEMMASCOPE-RES-131K
    7. 99847
    Prev
    Next
    INDEX
    Explanations

    pressure

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

    The neuron strongly activates on the word “pressure.”

    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
    The
    -2.48
    (
    -1.92
    I
    -1.85
     bronzo
    -1.84
     رائع
    -1.73
     あり
    -1.69
    菪
    -1.66
    縠
    -1.61
     الخارجية
    -1.61
     nomina
    -1.59
    POSITIVE LOGITS
     Pressure
    2.41
    pressure
    2.41
     pressure
    2.14
     presión
    2.08
    Pressure
    2.06
     давление
    1.85
     Druck
    1.76
     PRESSURE
    1.72
    Druck
    1.70
     The
    1.60
    Activations Density 0.028%

    No Known Activations