© 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. 104484
    Prev
    Next
    INDEX
    Explanations

    programming constructs and multilingual strings

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

    This neuron fires on functional/reactive API calls—especially map‐style operators (map, flatMap, switchMap) and related method invocations (subscribe, Promise, Right, etc.).

    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
     seo
    -1.00
     bijzondere
    -0.96
     sommige
    -0.94
     Некоторые
    -0.92
     propagan
    -0.90
     المثال
    -0.90
     liu
    -0.88
     البحث
    -0.88
     コットン
    -0.87
     incluso
    -0.85
    POSITIVE LOGITS
     through
    1.19
     taza
    1.04
     décembre
    0.96
    izacji
    0.96
     though
    0.95
    しますね
    0.95
     lados
    0.94
    southeast
    0.93
    zdroj
    0.92
    してます
    0.92
    Activations Density 0.008%

    No Known Activations