© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    list items and structures

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

    The neuron is triggered by backslash-initiated tokens, i.e. LaTeX (or similar) command markers.

    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
    Dining
    -0.81
    кну
    -0.80
     hunde
    -0.79
    šinou
    -0.78
     joc
    -0.78
     potest
    -0.77
    myModal
    -0.77
    湃
    -0.75
    یاد
    -0.75
     روسيا
    -0.75
    POSITIVE LOGITS
    item
    1.12
     item
    1.06
    Item
    0.95
    坟
    0.81
    ITEM
    0.81
     getItem
    0.79
     ItemType
    0.78
    getItem
    0.78
    li
    0.77
    itm
    0.77
    Activations Density 0.001%

    No Known Activations