© 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. 39906
    Prev
    Next
    INDEX
    Explanations

    sys import

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

    The neuron fires on tokens naming compatibility or configuration utility modules (e.g. “six,” “platform,” “compat,” “config.hpp,” etc.)—in other words, imports/includes of compatibility or platform‐version helper libraries.

    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
    szt
    -1.09
     圣诞
    -1.05
     querían
    -1.01
    ҂
    -1.01
    ivity
    -1.01
     排行
    -0.98
    izaron
    -0.96
     nyel
    -0.94
    灕
    -0.94
     として
    -0.93
    POSITIVE LOGITS
     européennes
    0.96
    ilesh
    0.91
    ริ
    0.87
    幾
    0.86
    tfrac
    0.84
     新
    0.84
    L
    0.84
     modern
    0.83
    E
    0.82
    bierz
    0.81
    Activations Density 0.003%

    No Known Activations