© 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. 10-GEMMASCOPE-RES-131K
    7. 11724
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

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

    empty square brackets used in code, markup, or formatting contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on literal square-bracket characters (“[”).

    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
     tijds
    -1.59
     cuidadosamente
    -1.52
    ebenarnya
    -1.51
     from
    -1.49
     Terbaru
    -1.45
     ($("#
    -1.37
     Layanan
    -1.37
    ссов
    -1.37
     οποίο
    -1.35
     Lengkap
    -1.35
    POSITIVE LOGITS
    arschu
    1.52
     heath
    1.52
    »,
    1.49
    лары
    1.49
    \%,
    1.45
     ‚
    1.43
    </b>
    1.41
    OrWhiteSpace
    1.40
     linguistique
    1.38
    am
    1.38
    Activations Density 0.008%

    No Known Activations