© 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. 93718
    Prev
    Next
    INDEX
    Explanations

    rural settlement

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

    This neuron fires on code import statements (lines beginning with “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
    /*.
    -1.00
     vectra
    -0.94
     jetta
    -0.92
     teatr
    -0.90
     skoda
    -0.89
     siyang
    -0.87
     nata
    -0.86
    客观
    -0.86
     fuis
    -0.86
     Spal
    -0.86
    POSITIVE LOGITS
     пунктов
    0.96
     occasionally
    0.96
    \}$,
    0.87
    connectionString
    0.84
               
    0.83
     here
    0.82
             
    0.82
    amini
    0.81
    eminent
    0.81
     biasanya
    0.80
    Activations Density 0.002%

    No Known Activations