© 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. 34-GEMMASCOPE-RES-131K
    7. 97928
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    The neuron strongly activates on non-finite verb forms—specifically gerunds (-ing) and past participles (-ed) rather than base-form verbs.

    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
     gérer
    -0.95
     vivent
    -0.94
    Mr
    -0.93
     kunnen
    -0.91
     торт
    -0.90
    Dante
    -0.88
     assurent
    -0.88
    middels
    -0.85
    now
    -0.85
    중
    -0.84
    POSITIVE LOGITS
     (
    1.16
     [
    1.09
    lcccccc
    0.96
    クリル
    0.93
    ))^{
    0.91
     two
    0.90
    ouille
    0.89
     three
    0.89
     seven
    0.87
     الطعام
    0.85
    Activations Density 0.004%

    No Known Activations