© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34644
    Prev
    Next
    INDEX
    Explanations

    \left( followed by math

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

    This neuron detects TeX-style delimiter commands (e.g. “\left” and “\right”).

    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
    hood
    -1.03
    حداث
    -0.76
    meisterschaft
    -0.73
    יך
    -0.73
    ତ
    -0.71
    Observable
    -0.71
    cení
    -0.71
    HOOD
    -0.70
     quiz
    -0.69
    绑定
    -0.69
    POSITIVE LOGITS
     abraz
    0.77
    ᠌
    0.77
    ⌃
    0.76
    cticide
    0.74
    overs
    0.74
     handed
    0.73
     twor
    0.73
     woody
    0.72
    ();*/
    0.71
    andeep
    0.71
    Activations Density 0.012%

    No Known Activations