© 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. 35268
    Prev
    Next
    INDEX
    Explanations

    programming language elements

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

    This neuron fires on snippets of code—things like identifiers, numeric literals, underscores, and other programming tokens.

    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
    ném
    -1.04
    beeren
    -0.99
    siyah
    -0.94
    uarts
    -0.91
    peugeot
    -0.91
    jovem
    -0.88
    maxi
    -0.88
    tanh
    -0.87
    muş
    -0.86
    auda
    -0.86
    POSITIVE LOGITS
     then
    0.99
    ('
    0.96
     something
    0.94
    :'
    0.93
    ing
    0.89
    Примі
    0.87
     '
    0.86
    mail
    0.85
    ed
    0.84
    质疑
    0.84
    Activations Density 0.072%

    No Known Activations