© 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. 84264
    Prev
    Next
    INDEX
    Explanations

    python __init__ method

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

    The neuron fires on Python’s “dunder” identifiers (names or tokens made of double underscores, e.g. `__init__`, `__get__`, 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_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
     lidé
    -1.95
     Geschä
    -1.83
    eſ
    -1.81
     récompense
    -1.80
     помогает
    -1.69
     tatsächlich
    -1.69
    跸
    -1.69
     ſever
    -1.68
     และ
    -1.66
     unſ
    -1.65
    POSITIVE LOGITS
    ");
    1.85
    </
    1.69
    —
    1.67
    ’
    1.66
     re
    1.63
    It
    1.62
    1.62
    </h2>
    1.55
     температур
    1.55
     \%$
    1.53
    Activations Density 0.002%
    No Known Activations