© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65717
    Prev
    Next
    INDEX
    Explanations

    foreign language grammatical elements

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

    The neuron strongly activates on very high‐frequency, common English function words (e.g. auxiliary verbs, modals, prepositions, and other frequent grammatical “stop” words).

    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
     kırmızı
    -0.91
     encor
    -0.90
     profesion
    -0.86
     行っ
    -0.86
    七夕
    -0.86
     dissi
    -0.85
     ungkap
    -0.85
     calça
    -0.80
    ongeza
    -0.80
     lạnh
    -0.79
    POSITIVE LOGITS
     giusta
    0.93
     seier
    0.90
    丹药
    0.89
    õe
    0.88
    ünste
    0.86
     feral
    0.86
     ansatte
    0.85
    釐
    0.84
     konge
    0.83
     scolas
    0.82
    Activations Density 0.102%

    No Known Activations