© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    python class __init__ methods

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

    The neuron detects Python’s special “dunder” method or attribute names (identifiers surrounded by double underscores).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OPEN
    0.61
     Genel
    0.61
     FAIL
    0.58
     __
    0.57
     LINE
    0.57
     filename
    0.56
     familial
    0.56
     Badal
    0.56
     textAlign
    0.55
    IGER
    0.55
    POSITIVE LOGITS
    init
    0.57
    |(
    0.57
    queryset
    0.55
    repr
    0.54
    тер
    0.54
    collation
    0.54
    itiis
    0.53
    reper
    0.52
    держа
    0.50
    εις
    0.50
    Activations Density 0.001%

    No Known Activations