© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12181
    Prev
    Next
    INDEX
    Explanations

    but

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

    The neuron detects parenthetical asides, i.e. text inside or immediately following parentheses.

    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
     bulunabilir
    -1.91
    翃
    -1.75
     katkıda
    -1.73
     quintessential
    -1.70
     Перейти
    -1.68
     değiştir
    -1.67
     theses
    -1.66
     ihtiyaç
    -1.66
     シャツ
    -1.64
    辚
    -1.64
    POSITIVE LOGITS
     but
    2.56
     had
    2.27
    They
    1.84
     has
    1.77
    g
    1.73
     took
    1.70
     went
    1.66
    ・・・
    1.65
     got
    1.64
     at
    1.61
    Activations Density 0.067%

    No Known Activations