© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27234
    Prev
    Next
    INDEX
    Explanations

    code imports

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

    The neuron activates on import statements (lines that begin with “import” and list a package or class).

    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
     bArr
    -1.05
    
    -1.00
     generó
    -1.00
    篋
    -0.99
    ăți
    -0.98
    futbolista
    -0.97
     tayang
    -0.96
     digelar
    -0.95
    metido
    -0.95
    zers
    -0.94
    POSITIVE LOGITS
     Grüßen
    1.15
     châ
    0.90
    שלום
    0.88
     fapt
    0.87
    Välislingid
    0.85
     cinematogra
    0.81
    Să
    0.81
    ление
    0.81
    左侧
    0.80
    曲は
    0.79
    Activations Density 0.005%

    No Known Activations