© 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. 84098
    Prev
    Next
    INDEX
    Explanations

    django migrations and code imports

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

    This neuron fires on the beginnings of Python class definitions (the “class ClassName(…)” pattern).

    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
    ၂
    -1.13
    тесь
    -1.10
    стов
    -1.05
    rosas
    -1.02
     зажига
    -0.98
    скать
    -0.95
     сковоро
    -0.94
    љено
    -0.94
     domés
    -0.94
    大臣
    -0.94
    POSITIVE LOGITS
    などで
    1.13
     queste
    1.10
     festge
    1.09
     essas
    1.06
     áng
    1.05
     xay
    1.05
     culoare
    1.03
     instead
    1.00
    );*/
    0.99
    邹
    0.99
    Activations Density 0.003%

    No Known Activations