© 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. 65109
    Prev
    Next
    INDEX
    Explanations

    programming imports and declarations

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

    The neuron fires on lines that introduce external dependencies—import (or use) statements and their accompanying namespace/module paths.

    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
     theyre
    -0.85
     Compared
    -0.81
     serre
    -0.80
    Зачем
    -0.79
     Assuming
    -0.78
    ческие
    -0.78
    BaseActivity
    -0.77
     MatDialog
    -0.76
     saudara
    -0.76
    ės
    -0.75
    POSITIVE LOGITS
     tinha
    1.00
     definiciones
    0.98
     equipamento
    0.92
    ('');
    0.91
     amarela
    0.80
    gola
    0.80
    BufferException
    0.79
     เพื่อ
    0.79
     wyposaż
    0.77
     sujeito
    0.77
    Activations Density 0.022%

    No Known Activations