© 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. 48271
    Prev
    Next
    INDEX
    Explanations

    presentations and historical events

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

    This neuron detects title or section‐header tokens—i.e. words, numbers, or punctuation that appear in headings, slide titles, or other prominent metadata rather than in running body text.

    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
    ​​​​​​​
    -0.96
    actie
    -0.91
    ⁠
    -0.90
    ванием
    -0.88
     приведен
    -0.87
    istisch
    -0.87
    جستارهای
    -0.87
        
    -0.86
     
    -0.85
    帮我
    -0.84
    POSITIVE LOGITS
     presentation
    1.54
     presentations
    1.53
     slides
    1.50
     slide
    1.45
    presentation
    1.42
     lecture
    1.39
     Slide
    1.37
    slide
    1.36
     Presented
    1.35
    Agenda
    1.30
    Activations Density 0.090%

    No Known Activations