© 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. 22-GEMMASCOPE-RES-131K
    7. 9803
    Prev
    Next
    INDEX
    Explanations

    ending or removal

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

    The neuron fires on words that introduce or mark dependencies and conditional relationships in technical or scientific descriptions (e.g. “dependent,” “reversible by,” “after,” “when”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Sucesor
    -0.94
     tweede
    -0.90
     aceptación
    -0.88
    ก่
    -0.82
    olahan
    -0.80
    luo
    -0.80
     ayudan
    -0.79
    inales
    -0.79
    isan
    -0.78
    НІ
    -0.77
    POSITIVE LOGITS
     cease
    1.40
     прекра
    1.35
     ceases
    1.34
     ceased
    1.30
     переста
    1.25
     remove
    1.14
     cessation
    1.05
     ceasing
    1.05
     hết
    1.02
     after
    1.01
    Activations Density 0.066%

    No Known Activations