© 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. 32641
    Prev
    Next
    INDEX
    Explanations

    closing brace/bracket/tag

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

    The neuron fires strongly on closing‐structure tokens (e.g. ‘}’, ‘},’, and closing XML/HTML tags), i.e. ends of code or markup blocks.

    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
     membag
    -1.05
     melap
    -1.02
    )();
    -0.99
     berken
    -0.98
     foncé
    -0.96
     then
    -0.96
    -0.95
    Экономи
    -0.93
     sabar
    -0.93
     as
    -0.92
    POSITIVE LOGITS
     unseres
    1.03
    Ằ
    0.99
     bian
    0.99
    ldt
    0.98
    liere
    0.97
     vermelho
    0.96
     Exclu
    0.96
     estudar
    0.95
    </sup>
    0.89
     vorüber
    0.88
    Activations Density 0.006%

    No Known Activations