© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129591
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for occurrences of the “using” keyword (i.e. import/using statements) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    San Francisco

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    vertissement
    -1.10
    kleidung
    -1.10
    蚰
    -1.10
     klinik
    -1.06
    vereignty
    -1.05
     และ
    -1.03
     AspNetCore
    -1.02
     policía
    -1.02
     témoignages
    -1.00
    目
    -1.00
    POSITIVE LOGITS
    باح
    1.13
    ukunfts
    1.11
    じた
    1.08
    足够的
    1.05
     about
    1.04
     Thirty
    1.02
    灕
    1.01
     where
    1.00
     則
    0.99
     比較
    0.99
    Activations Density 0.001%

    No Known Activations