© 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. 22-GEMMASCOPE-RES-131K
    7. 93331
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

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

    The neuron fires on isolated code‐identifier tokens (e.g. variable, function, class, or keyword names) embedded in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    得太
    -1.03
    tisti
    -1.02
    过来了
    -1.01
     navideñas
    -1.00
     Алексей
    -0.99
     آوری
    -0.99
     ответить
    -0.95
     Meksi
    -0.94
     Desember
    -0.94
    깁
    -0.93
    POSITIVE LOGITS
     pracuje
    1.07
     alguns
    1.03
    を選択します
    0.98
    亠
    0.97
    を探す
    0.94
    いえ
    0.93
    время
    0.91
     ozdob
    0.91
    cocina
    0.90
     okna
    0.90
    Activations Density 0.007%

    No Known Activations