© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    programming assignment operators

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

    The neuron responds to assignment or augmentation operators (e.g. “+=”, “:=”, “.=”) across code snippets.

    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
    It
    -1.50
    感じです
    -1.46
     jesteś
    -1.45
    為に
    -1.45
    感じで
    -1.45
    ところに
    -1.42
     wiesz
    -1.41
     mały
    -1.41
     bulunabilir
    -1.39
     nią
    -1.37
    POSITIVE LOGITS
     (
    1.75
     in
    1.69
     “
    1.37
     "
    1.37
    یکر
    1.30
     '
    1.28
    >?
    1.28
    子が
    1.24
    錚
    1.23
     （
    1.22
    Activations Density 0.002%

    No Known Activations