© 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. 85709
    Prev
    Next
    INDEX
    Explanations

    Cartesian coordinates and Pascal programs

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

    The neuron activates on mentions of “Cartesian” (e.g. Cartesian product or Cartesian 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
    蹓
    -2.81
    犼
    -2.55
    颪
    -2.45
    取决
    -2.36
    Ꮏ
    -2.34
     lomba
    -2.31
    ся
    -2.25
     geforce
    -2.23
     itſelf
    -2.20
     mense
    -2.19
    POSITIVE LOGITS
    of
    2.56
    m
    2.22
    To
    2.22
    after
    2.19
     various
    2.09
    on
    2.08
     Cartesian
    2.08
    ”،
    2.02
    er
    2.00
     your
    2.00
    Activations Density 0.005%

    No Known Activations