© 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. 49663
    Prev
    Next
    INDEX
    Explanations

    coordinate

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

    The neuron fires on promotional product descriptions—particularly style, material, and design attribute words (e.g. minimalistic, leather, contemporary, jacket).

    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
     Supremo
    -0.90
    fiée
    -0.89
    ární
    -0.88
     viêm
    -0.86
    ılacak
    -0.82
     when
    -0.80
    ıldığı
    -0.79
     duidelijk
    -0.78
    سيم
    -0.77
    angue
    -0.76
    POSITIVE LOGITS
    coordinate
    1.03
    Coordinate
    1.00
     items
    0.98
     coordination
    0.98
     DI
    0.95
    COORD
    0.94
     coordinate
    0.94
     POINT
    0.93
     Coordinate
    0.93
     item
    0.92
    Activations Density 0.005%

    No Known Activations