© 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. 39345
    Prev
    Next
    INDEX
    Explanations

    code separators

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

    The neuron fires on the names of modules or classes being imported—that is, the identifiers that follow `import` (and file-path) statements.

    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
     espanhol
    -1.06
    Qc
    -0.91
     probable
    -0.90
     abstrato
    -0.87
    艶
    -0.84
     portugués
    -0.83
     dismin
    -0.83
     hidratante
    -0.81
     Trop
    -0.81
    ぼう
    -0.81
    POSITIVE LOGITS
     or
    1.11
     Campionato
    0.92
    Или
    0.88
    或者
    0.86
    ﹔
    0.86
    或
    0.84
    หรือ
    0.81
     альтерна
    0.77
    bardziej
    0.76
    而非
    0.76
    Activations Density 0.021%

    No Known Activations