© 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. 10-GEMMASCOPE-RES-131K
    7. 128945
    Prev
    Next
    INDEX
    Explanations

    mathematical statements and questions

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

    The neuron activates on numeric literals—especially those containing decimal points or fractional expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Both
    -2.00
    😱
    -1.91
     and
    -1.91
     nowa
    -1.89
    💁
    -1.75
     titulada
    -1.72
     they
    -1.70
    tttt
    -1.70
    tly
    -1.67
     ！
    -1.67
    POSITIVE LOGITS
    你需要
    2.00
     маленьких
    1.98
     různých
    1.96
    紲
    1.95
    厹
    1.95
    倂
    1.94
    平常
    1.88
     высокая
    1.84
    懨
    1.82
    푣
    1.81
    Activations Density 0.031%

    No Known Activations