© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    advances and improvements

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

    The neuron strongly activates on specialized, content-heavy terms and phrasing typical of formal scientific or academic writing.

    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
    ικού
    -1.03
    NhanVien
    -0.97
    wijze
    -0.95
    illingham
    -0.95
    ріб
    -0.94
    nasium
    -0.93
    娅
    -0.90
    未來
    -0.90
     zonder
    -0.90
     activiteiten
    -0.90
    POSITIVE LOGITS
     advances
    2.39
     advancements
    2.28
     improvements
    2.11
     improved
    2.05
    Advances
    2.02
     technology
    1.96
     developments
    1.84
    Improvements
    1.77
     availability
    1.77
     technologies
    1.77
    Activations Density 0.381%

    No Known Activations