© 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. 20922
    Prev
    Next
    INDEX
    Explanations

    symmetry breaking

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

    The neuron detects occurrences of the term “symmetry” (and closely related technical mentions of symmetry) in scientific text.

    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
    ！"
    -2.44
     –
    -2.42
    ?"
    -2.38
    😦
    -2.16
    醱
    -2.14
    ㅅ
    -2.05
    埽
    -2.05
     позволяет
    -2.03
    ㅂ
    -2.03
     של
    -2.02
    POSITIVE LOGITS
    趼
    3.17
    噲
    2.53
     hvem
    2.48
     folgender
    2.27
    Ꮸ
    2.19
    e
    2.17
    THEY
    2.14
    だけではなく
    2.13
     женщины
    2.11
     salvaje
    2.11
    Activations Density 0.008%

    No Known Activations