© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11787
    Prev
    Next
    INDEX
    Explanations

    statistical modeling

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

    This neuron responds to technical research‐paper tokens such as numeric values, section labels, and statistical model names or acronyms.

    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
    ذت
    -0.71
     Slaughter
    -0.71
    toolStripButton
    -0.71
    位の
    -0.71
     otto
    -0.69
    劇情
    -0.69
     운
    -0.69
     ведет
    -0.68
    čního
    -0.68
     Xunit
    -0.68
    POSITIVE LOGITS
     models
    1.27
     Bayesian
    1.23
     modelos
    1.07
     Models
    1.06
    models
    1.05
     latent
    1.02
     модели
    1.00
     longitudinal
    0.96
     interrupted
    0.95
     modèles
    0.94
    Activations Density 0.216%

    No Known Activations