© 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. 20646
    Prev
    Next
    INDEX
    Explanations

    pressurized fluid or gas

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

    The neuron fires on words related to pressure or pressurization (e.g. “pressure,” “pressurize,” “pressurized”).

    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
    "
    -2.89
    I
    -2.61
    (
    -2.23
     pernicious
    -2.06
    ).
    -1.97
    .“
    -1.91
    .''
    -1.91
    1
    -1.88
    [
    -1.88
     occasional
    -1.84
    POSITIVE LOGITS
    俢
    2.27
    梣
    2.16
    艄
    2.09
    ⩴
    2.09
    就不是
    2.08
    鲀
    2.05
    數
    1.95
    缡
    1.95
    bbles
    1.92
     candidat
    1.90
    Activations Density 0.011%

    No Known Activations