© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59516
    Prev
    Next
    INDEX
    Explanations

    Python class definitions

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

    This neuron detects Python class‐definition lines (i.e. the “class” keyword marking a class declaration).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𝄆
    -1.80
    thschild
    -1.78
    ༀ
    -1.73
    slavery
    -1.71
    伥
    -1.70
    ㌧
    -1.67
    Çok
    -1.66
    ⢇
    -1.66
    ."
    -1.66
    ↵
    -1.65
    POSITIVE LOGITS
    ers
    2.30
    am
    2.25
    …”
    2.08
     Nevertheless
    1.98
    ！」
    1.88
     Nonetheless
    1.86
     tinge
    1.82
    I
    1.80
     not
    1.79
     Fundament
    1.77
    Activations Density 0.013%

    No Known Activations