© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56697
    Prev
    Next
    INDEX
    Explanations

    `from` python imports

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

    The neuron is detecting Python code tokens (especially common keywords like import, from, class, and other code‐specific symbols)

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    tutup
    -0.74
    josé
    -0.73
     đạo
    -0.72
    𝘕
    -0.72
    fortunes
    -0.72
     governador
    -0.71
     predecessors
    -0.71
    eslint
    -0.71
     schli
    -0.69
    Trichloroethane
    -0.68
    POSITIVE LOGITS
     django
    1.50
     rest
    1.30
     apps
    1.20
     accounts
    1.04
     app
    0.99
     APP
    0.98
     datetime
    0.96
    rest
    0.94
    APP
    0.94
     Nouvelle
    0.90
    Activations Density 0.008%

    No Known Activations