© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65991
    Prev
    Next
    INDEX
    Explanations

    import statements following punctuation

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

    The neuron spikes on long qualified import or package‐declaration lines in source code.

    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
     escribiendo
    -0.91
     kommunik
    -0.90
    referrer
    -0.88
    тых
    -0.87
    gemeen
    -0.86
    啲
    -0.86
    的关键
    -0.86
     gminy
    -0.85
     jahre
    -0.85
    cinnati
    -0.84
    POSITIVE LOGITS
     bekommen
    1.05
     this
    1.00
    が行
    0.90
     ſi
    0.89
     IFT
    0.89
     Frit
    0.88
     tind
    0.87
    tritts
    0.85
    licité
    0.85
     Cio
    0.85
    Activations Density 0.035%

    No Known Activations