© 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. 26588
    Prev
    Next
    INDEX
    Explanations

    Python imports

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

    This neuron detects Python “import” statements (i.e. lines or tokens that bring modules or symbols into a script).

    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
     reizen
    -1.23
     bewegen
    -1.20
     realidade
    -1.11
     imprensa
    -1.11
     felicidade
    -1.10
     identidade
    -1.10
     personalidade
    -1.10
     allerlei
    -1.06
     angebra
    -1.05
     Balkon
    -1.02
    POSITIVE LOGITS
     how
    1.50
     specifica
    1.39
     electrica
    1.32
     destina
    1.27
     bianchi
    1.27
     activa
    1.23
     logica
    1.23
     produt
    1.23
     *
    1.22
     modifica
    1.21
    Activations Density 0.010%

    No Known Activations