© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77398
    Prev
    Next
    INDEX
    Explanations

    python logging gzip deflate

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

    The neuron fires on occurrences of the word “logging” (i.e. when the code is importing or using the logging module).

    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
     @(
    -0.64
    Раз
    -0.63
     منح
    -0.63
     fejles
    -0.63
    лений
    -0.63
     élé
    -0.63
     reconn
    -0.62
    黙
    -0.62
    ACING
    -0.61
    崁
    -0.61
    POSITIVE LOGITS
    pink
    0.70
    rett
    0.68
    ensemble
    0.65
    を持った
    0.65
    pine
    0.65
    pull
    0.64
    entiment
    0.64
    identity
    0.63
     Gaud
    0.63
     Pink
    0.62
    Activations Density 0.071%

    No Known Activations