© 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. 10-GEMMASCOPE-RES-131K
    7. 8759
    Prev
    Next
    INDEX
    Explanations

    I am doing

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

    This neuron detects C/C++ “#include” directives that use angle-bracket header names (e.g. #include <termios.h>).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    وروبا
    -1.13
    nanoTime
    -1.12
    iertas
    -1.03
     וגם
    -0.99
     tiež
    -0.98
    ciless
    -0.98
     simply
    -0.98
     interessa
    -0.98
    layers
    -0.97
     マイク
    -0.97
    POSITIVE LOGITS
     
    1.16
    cijos
    1.12
    []}
    1.05
     UIFont
    1.05
    thmus
    1.03
    potamus
    1.03
    ToLoad
    1.02
    ̶
    1.02
     Сто
    1.01
     الطريق
    1.00
    Activations Density 0.260%

    No Known Activations