© 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. 32916
    Prev
    Next
    INDEX
    Explanations

    code imports or definitions

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

    This neuron detects tokens that are part of import- or package-style module names (library/package paths) 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_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
     would
    -1.06
     Walk
    -1.01
     invece
    -0.98
    在了
    -0.98
     jeżeli
    -0.98
    ᵣ
    -0.98
     erneu
    -0.96
     Ow
    -0.94
     jūs
    -0.94
     jugando
    -0.93
    POSITIVE LOGITS
    <bos>
    1.09
    がありますが
    1.06
     Manfaat
    1.04
     geometr
    1.01
     Lakukan
    0.98
     Pastikan
    0.95
    kapelle
    0.94
    Чем
    0.94
     Mungkin
    0.94
     Perlu
    0.94
    Activations Density 0.035%

    No Known Activations