© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48395
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron identifies numeric tokens (including integers, decimals, and hexadecimal numbers).

    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
    пература
    -1.66
    蛧
    -1.66
    älfte
    -1.42
    自行车
    -1.42
     francesa
    -1.38
    CURLOPT
    -1.38
     מים
    -1.36
    ！　
    -1.36
    江南
    -1.35
    ;%%
    -1.34
    POSITIVE LOGITS
    :
    1.59
    .
    1.57
     AVEC
    1.52
    種類の
    1.50
     etc
    1.49
     Ajouter
    1.47
     ITAL
    1.45
    voyez
    1.44
    ことはありません
    1.39
     taas
    1.36
    Activations Density 0.008%

    No Known Activations