© 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. 22-GEMMASCOPE-RES-131K
    7. 67770
    Prev
    Next
    INDEX
    Explanations

    programming imports and libraries

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

    The neuron fires on module specifier string literals in import statements.

    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
     páss
    -1.22
     by
    -1.15
    ಱ
    -1.15
     Não
    -1.15
     étions
    -1.14
     leão
    -1.13
     not
    -1.11
    lijken
    -1.09
     jornalista
    -1.09
     their
    -1.05
    POSITIVE LOGITS
    Hilsen
    1.08
    ised
    1.08
    ↵↵
    1.05
    擅长
    1.04
     scorso
    1.02
     כאשר
    1.02
    He
    1.00
    するため
    0.99
     greate
    0.99
    mRecyclerView
    0.98
    Activations Density 0.004%

    No Known Activations