© 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. 34-GEMMASCOPE-RES-131K
    4. 30159
    Prev
    Next
    INDEX
    Explanations

    global variables and imports

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

    The neuron flags PHP variable‐scope tokens—particularly uses of “global” and “$” (e.g. `$GLOBALS`, `global`, `isset($…)`).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    }]$
    -0.91
     =
    -0.88
    licazione
    -0.87
    ਯ
    -0.86
     while
    -0.86
    })$
    -0.84
    čných
    -0.81
     [
    -0.81
     krijgen
    -0.81
    }(\
    -0.80
    POSITIVE LOGITS
     Eu
    1.09
    __;
    1.06
     Rein
    0.95
     GLO
    0.94
     uLocal
    0.93
    ตู
    0.92
     condu
    0.91
     Gla
    0.91
     logger
    0.90
     riun
    0.90
    Activations Density 0.006%

    No Known Activations