© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117131
    Prev
    Next
    INDEX
    Explanations

    Android, Emoji, Q, Characterization

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

    The neuron is tuned to the signature tokens of the compiled Babel interop helper (the `_interopRequireDefault` function) used to handle default exports in JavaScript modules.

    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
     sinon
    -0.97
    níka
    -0.96
     countless
    -0.94
     or
    -0.93
    時尚
    -0.88
     уход
    -0.87
     museo
    -0.85
    izado
    -0.85
    钓鱼
    -0.84
    
    -0.84
    POSITIVE LOGITS
    ledu
    0.99
     באמצעות
    0.96
     igualdad
    0.96
     večer
    0.94
    似乎
    0.90
     taki
    0.90
    onents
    0.88
     одному
    0.87
    ジュー
    0.86
    bca
    0.85
    Activations Density 0.003%

    No Known Activations