© 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. 71319
    Prev
    Next
    INDEX
    Explanations

    coordinates

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

    The neuron is triggered by occurrences of “coordinate” (e.g. “Coordinates,” “coordinates”).

    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
    其他
    -2.52
    ."
    -2.45
     ersche
    -2.44
    ⎚
    -2.36
    டன்
    -2.36
    ?"
    -2.31
     '
    -2.31
    gefügt
    -2.30
    说
    -2.30
    enablog
    -2.28
    POSITIVE LOGITS
    ↵
    3.84
    哢
    3.84
    ”،
    3.41
    ”.
    3.11
    !”
    2.83
     “
    2.73
    ”)
    2.73
    зации
    2.67
    鱘
    2.64
    勍
    2.63
    Activations Density 0.012%

    No Known Activations