© 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. 34-GEMMASCOPE-RES-131K
    7. 81665
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    This neuron detects import or “using” statements that reference the IO library (i.e. the token “IO” in an import).

    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
    気の
    -0.84
    ！　
    -0.81
    ᴀ
    -0.74
    verein
    -0.72
     bude
    -0.72
    ators
    -0.71
    スキ
    -0.71
    ţii
    -0.70
     substrate
    -0.70
    tization
    -0.69
    POSITIVE LOGITS
     reader
    1.08
     Directory
    0.96
    Directory
    0.89
     Rudolph
    0.89
     directory
    0.88
     Stream
    0.88
     Reader
    0.84
     Path
    0.77
    нта
    0.77
    Rud
    0.77
    Activations Density 0.004%

    No Known Activations