© 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. 34-GEMMASCOPE-RES-131K
    7. 92008
    Prev
    Next
    INDEX
    Explanations

    spaces and chambers

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

    The neuron is detecting mentions of physical pressure measurements and related sensing instrumentation (e.g., air or fluid pressure sensing).

    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
     DOOR
    -0.88
     fences
    -0.87
     doors
    -0.83
    ҩ
    -0.82
     板
    -0.82
     door
    -0.81
    cliff
    -0.80
     façade
    -0.79
    Automat
    -0.79
    door
    -0.78
    POSITIVE LOGITS
     cavity
    2.03
     chamber
    1.88
     cavities
    1.60
     space
    1.59
     spaces
    1.48
     chambers
    1.46
    cavity
    1.35
    空间
    1.27
    chamber
    1.27
     compartments
    1.24
    Activations Density 0.288%

    No Known Activations