© 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. 12267
    Prev
    Next
    INDEX
    Explanations

    technical or scientific questions

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

    The neuron strongly activates on Python “import” statements, especially the tokens around “from … import …” module‐import syntax.

    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
    myapp
    -0.91
    brazilian
    -0.85
    trump
    -0.81
    黑暗
    -0.79
     MessageBoxIcon
    -0.75
     Visit
    -0.75
    tvguide
    -0.75
    playstation
    -0.75
     Identify
    -0.74
    cruel
    -0.73
    POSITIVE LOGITS
     handi
    0.92
    HandleFunc
    0.91
    echo
    0.87
    Ud
    0.85
     sarcas
    0.84
     dispatcher
    0.83
    前回の
    0.82
     CIN
    0.82
     ARB
    0.82
     arbore
    0.82
    Activations Density 0.006%

    No Known Activations