© 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. 26582
    Prev
    Next
    INDEX
    Explanations

    module imports

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

    The neuron activates on module import or require statements (i.e. lines that load external or local dependencies).

    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
     &
    -0.93
     　
    -0.93
     #
    -0.93
    ＆
    -0.93
    仍然
    -0.90
    UnityEngine
    -0.90
    ‐
    -0.89
    ‛
    -0.88
    ments
    -0.88
    ،
    -0.88
    POSITIVE LOGITS
    Kilder
    1.00
    সং
    0.98
     buurt
    0.89
    ьера
    0.88
     compe
    0.86
     squa
    0.86
     kontroli
    0.86
    ñor
    0.86
    Cair
    0.85
     groei
    0.85
    Activations Density 0.004%

    No Known Activations