© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 127710
    Prev
    Next
    INDEX
    Explanations

    The neuron is specifically detecting occurrences of the Python keyword “as” (e.g. in import alias statements).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    import as np or pd

    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
    Negative Logits
     from
    -1.54
     each
    -1.37
    篭
    -1.34
     by
    -1.33
     of
    -1.32
     all
    -1.20
     '\\;'
    -1.16
     OSError
    -1.12
    AnchorStyles
    -1.09
     invokingState
    -1.07
    POSITIVE LOGITS
     fie
    1.11
    ⼯
    1.09
    enquête
    1.09
     намного
    1.09
    θη
    1.08
    ↵↵
    1.06
    interpr
    1.06
    冋
    1.05
    Tobi
    1.05
    grenze
    1.05
    Activations Density 0.002%

    No Known Activations