© 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. 108832
    Prev
    Next
    INDEX
    Explanations

    text

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

    The neuron fires most strongly at the opening of deeply nested object structures in code (e.g. JSON objects nested several levels deep).

    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
     должен
    -0.98
     diputado
    -0.91
     propiedad
    -0.90
     podróż
    -0.88
    情報を
    -0.86
    ṃ
    -0.86
    作品の
    -0.86
     modalidades
    -0.84
    厚度
    -0.84
     记
    -0.83
    POSITIVE LOGITS
     text
    1.97
    mtext
    1.46
    innerText
    1.16
     bluzka
    1.15
    Text
    1.15
     texts
    1.14
    nexo
    1.13
     textu
    1.12
     текста
    1.10
    getText
    1.09
    Activations Density 0.025%

    No Known Activations