© 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. 66065
    Prev
    Next
    INDEX
    Explanations

    importing components or services

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

    This neuron detects named imports—specifically the identifiers of classes, components, or services being imported in code.

    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
    蚰
    -1.83
     kompati
    -1.79
     parfü
    -1.76
    Ꮔ
    -1.60
     parfüm
    -1.60
     nyeri
    -1.60
     reizen
    -1.60
     Hacer
    -1.57
     praktis
    -1.55
     anún
    -1.55
    POSITIVE LOGITS
     In
    1.58
     l
    1.45
     you
    1.43
     N
    1.42
     How
    1.41
    1.41
     W
    1.38
     P
    1.37
     O
    1.37
     m
    1.35
    Activations Density 0.001%
    No Known Activations