© 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. 22-GEMMASCOPE-RES-131K
    7. 15615
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron activates on programming import/include lines that specify language or system libraries (e.g. “dart:typed_data”, “dart:ui”, or “<UIKit/UIKit.h>”).

    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
    ₽
    -1.02
     gerçekten
    -0.99
    mę
    -0.97
    stanz
    -0.96
    зможно
    -0.94
    感じで
    -0.93
     acostumb
    -0.92
     लंब
    -0.91
    :[],
    -0.91
    itrile
    -0.91
    POSITIVE LOGITS
    aggiare
    1.04
    structing
    0.99
     importing
    0.94
    ätigung
    0.94
     Longitud
    0.94
     utilisent
    0.94
    unfortunately
    0.92
    otropy
    0.92
    juries
    0.91
    vierno
    0.91
    Activations Density 0.002%

    No Known Activations