© 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. 70751
    Prev
    Next
    INDEX
    Explanations

    code structure and questions

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

    The neuron activates on the Java “public class …” declaration (the tokens “public,” “class,” and the class name).

    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
     their
    -1.29
     such
    -1.03
     cosi
    -0.96
    化する
    -0.94
     of
    -0.93
     becoming
    -0.93
     getting
    -0.92
    വി
    -0.92
    なのでしょう
    -0.91
     Franti
    -0.91
    POSITIVE LOGITS
    parece
    1.09
     nové
    1.06
     Leitung
    1.05
     трени
    1.03
     tortura
    1.02
    dây
    1.00
     griechischen
    1.00
    ItemName
    0.99
    dafx
    0.98
    Chiara
    0.98
    Activations Density 0.002%

    No Known Activations