© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54372
    Prev
    Next
    INDEX
    Explanations

    programming languages and frameworks

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

    The neuron detects mentions of programming languages or frameworks (e.g., Django, Laravel, Python, PHP, Angular) in the text.

    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
     muualla
    -1.34
    abinieri
    -1.34
    zeera
    -1.32
     signifikan
    -1.27
    Publié
    -1.21
    kleine
    -1.21
     نزد
    -1.21
     casó
    -1.20
    orithmic
    -1.20
    さぁ
    -1.18
    POSITIVE LOGITS
     sprzedaży
    1.22
     you
    1.20
     prostředí
    1.15
     Benutz
    1.13
    ↵↵
    1.13
     egens
    1.09
     version
    1.08
    らしいです
    1.05
    があります
    1.05
    もあって
    1.04
    Activations Density 0.388%

    No Known Activations