© 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. 22-GEMMASCOPE-RES-131K
    4. 70674
    Prev
    Next
    INDEX
    Explanations

    code structure markers

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

    The neuron fires on import statements pulling in operator‐style modules (e.g. “rxjs/operators”).

    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
    difice
    -1.02
     inwest
    -0.98
     指
    -0.92
     estuche
    -0.91
     faptul
    -0.88
    在此
    -0.87
     üzerinde
    -0.86
    hilterra
    -0.85
    hline
    -0.84
     jonka
    -0.84
    POSITIVE LOGITS
     when
    1.04
    viembre
    1.02
    vaders
    0.98
    isValid
    0.96
    دانلود
    0.93
     plass
    0.93
     nemo
    0.93
    vocations
    0.91
    kkor
    0.90
    {~
    0.90
    Activations Density 0.000%

    No Known Activations