© 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. 58
    Prev
    Next
    INDEX
    Explanations

    application and navigation links

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

    The neuron fires on CamelCase API‐style identifiers and method names in code (e.g. navigation, applicationDidBecomeActive, shouldAutorotate).

    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
    傚
    -1.07
    更大的
    -0.96
     попробовать
    -0.89
     diagrama
    -0.88
    ttää
    -0.87
    阴影
    -0.86
     debilidad
    -0.86
     tristes
    -0.85
     delicioso
    -0.85
     полного
    -0.85
    POSITIVE LOGITS
    шей
    1.05
    Preparazione
    1.03
    лиза
    1.01
     înainte
    0.99
    unteering
    0.97
     però
    0.97
    即将
    0.96
     Erkrankungen
    0.96
     bowiem
    0.96
    Preparación
    0.94
    Activations Density 0.000%

    No Known Activations