© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106534
    Prev
    Next
    INDEX
    Explanations

    kernel code and scientific abstracts

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

    The neuron is essentially keyed to the syntax of C function definitions (e.g. the “int dev_open( struct inode *inode, struct file *filp )” pattern). It lights up on the tokens that appear when you start a C function signature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    getBoolean
    -0.79
    travis
    -0.79
    超市
    -0.77
    yeli
    -0.77
    prow
    -0.77
     largura
    -0.71
     اط
    -0.70
    wasi
    -0.69
    itse
    -0.69
    Wars
    -0.69
    POSITIVE LOGITS
    字符
    0.88
    printk
    0.87
     USO
    0.85
     EXPORT
    0.83
    sema
    0.81
    EXPORT
    0.81
    kz
    0.80
    Module
    0.79
     Cyan
    0.78
    avimas
    0.75
    Activations Density 0.035%

    No Known Activations