© 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. 34-GEMMASCOPE-RES-131K
    7. 78465
    Prev
    Next
    INDEX
    Explanations

    icon-related keywords and code

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

    The neuron strongly activates on code‐related or technical tokens—things like programming keywords, identifiers, class or package names, constants, and other non-natural-language symbols.

    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
    らく
    -0.71
     zeta
    -0.71
    补贴
    -0.69
     voldo
    -0.69
    داية
    -0.67
     mendatang
    -0.67
     Bookmark
    -0.66
     misfortunes
    -0.66
    vieran
    -0.66
    Bookmark
    -0.65
    POSITIVE LOGITS
    setIcon
    1.41
    ImageIcon
    1.34
     ImageIcon
    1.16
    getIcon
    1.14
     Icon
    1.07
    Icon
    0.96
    ICON
    0.93
     ICON
    0.93
    licon
    0.91
    icon
    0.88
    Activations Density 0.001%

    No Known Activations