© 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. 34-GEMMASCOPE-RES-131K
    7. 99016
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and ratings

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

    The neuron activates on quantitative specifications—that is, numbers and measurement context (units, ratings, outputs) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     incluir
    -1.11
    asible
    -1.01
    ถ้า
    -0.97
    Hà
    -0.94
     czasu
    -0.94
    经典
    -0.93
    estilo
    -0.92
    IonicModule
    -0.92
     času
    -0.91
     vhod
    -0.89
    POSITIVE LOGITS
     numbers
    1.49
     measurement
    1.42
     ratings
    1.41
     rating
    1.36
    数字
    1.29
    numbers
    1.22
    orthand
    1.21
    数値
    1.20
     misleading
    1.20
     циф
    1.18
    Activations Density 0.065%

    No Known Activations