© 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. 34-GEMMASCOPE-RES-131K
    4. 65939
    Prev
    Next
    INDEX
    Explanations

    `. field attr external condition email`

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

    The neuron strongly activates on programming‐style identifiers and method names (especially Python/matplotlib variable names like “ax,” function calls like “subplots,” and chained attribute accesses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    发送
    -0.77
    namental
    -0.75
     máu
    -0.74
     Lp
    -0.73
     PARAMETERS
    -0.73
    )^{-
    -0.72
     喷
    -0.72
    负
    -0.71
    PAUSE
    -0.71
     Taille
    -0.71
    POSITIVE LOGITS
    Climat
    0.71
    Allez
    0.69
    ész
    0.67
     EVERY
    0.67
    長の
    0.66
     və
    0.65
    Πα
    0.65
    рядок
    0.65
    pubsub
    0.65
     thích
    0.64
    Activations Density 0.027%

    No Known Activations