© 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. 130283
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals (digits and numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    liš
    -0.89
     mør
    -0.88
    ingin
    -0.86
    刘
    -0.86
    ötzlich
    -0.84
    🗞
    -0.84
    BuilderFactory
    -0.83
    หรือ
    -0.82
    hender
    -0.82
     säl
    -0.82
    POSITIVE LOGITS
     local
    0.86
     No
    0.85
     queste
    0.85
     C
    0.84
     N
    0.82
    只有一个
    0.82
     allgeme
    0.81
     these
    0.80
    local
    0.79
    这点
    0.79
    Activations Density 0.003%

    No Known Activations