© 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. 100402
    Prev
    Next
    INDEX
    Explanations

    has had have created occurred launched

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

    The neuron is sensitive to numeric data—especially measured values, statistics, percentages, and other numerical 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
    Their
    -1.45
     圓
    -1.39
     will
    -1.34
    Quite
    -1.34
     actually
    -1.30
    ğer
    -1.29
     區
    -1.29
    Langkah
    -1.28
    Also
    -1.27
     Therefore
    -1.27
    POSITIVE LOGITS
     it
    1.43
     tenuto
    1.30
    “
    1.27
               
    1.20
    internalType
    1.17
                 
    1.16
    需要
    1.16
     幸
    1.14
     necesit
    1.14
     hô
    1.14
    Activations Density 0.175%

    No Known Activations