© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22538
    Prev
    Next
    INDEX
    Explanations

    multilingual content and code snippets

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

    The neuron activates on standalone numeric literals (integers or decimals) in the text.

    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
     jong
    -1.66
     parlement
    -1.63
     Parfum
    -1.63
     tôt
    -1.56
    2
    -1.54
     neder
    -1.50
    ronomie
    -1.50
     capot
    -1.49
     Caribe
    -1.48
    ANE
    -1.46
    POSITIVE LOGITS
     by
    1.98
     the
    1.97
     their
    1.61
    lanterna
    1.58
    紆
    1.53
     entire
    1.52
     variados
    1.49
    表達
    1.46
     graciosos
    1.44
     terciopelo
    1.44
    Activations Density 0.003%

    No Known Activations