© 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. 130200
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out integer literals (numeric tokens) in the code or markup.

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

    file path separators or code structure

    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
     when
    -1.48
     новые
    -1.09
     acús
    -1.07
    phòng
    -1.04
     while
    -1.04
    sprzed
    -1.02
    giày
    -0.98
    źródło
    -0.97
    akyti
    -0.96
    興奮
    -0.94
    POSITIVE LOGITS
    しば
    1.14
     anderem
    1.13
    It
    1.12
    na
    1.11
     costumbres
    1.09
    called
    1.09
     chỉ
    1.08
    z
    1.06
    co
    1.06
    hu
    1.05
    Activations Density 0.001%

    No Known Activations