© 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. 10-GEMMASCOPE-RES-131K
    7. 28953
    Prev
    Next
    INDEX
    Explanations

    list item and markup delimiters

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

    The neuron fires on tokens that mark the start of a new formatted block—e.g. “A:” answer labels or LaTeX “\begin{…}” environment commands.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ，
    -1.85
     offerte
    -1.63
    ︐
    -1.62
    Отлич
    -1.59
    Уже
    -1.55
     délicieux
    -1.55
    骉
    -1.51
     poivre
    -1.50
     importants
    -1.49
    
    -1.49
    POSITIVE LOGITS
     one
    1.77
     decorados
    1.61
     time
    1.56
     conocidas
    1.55
     methods
    1.54
     on
    1.54
     recientemente
    1.53
     north
    1.52
    '}}>
    1.50
     nowadays
    1.49
    Activations Density 0.003%

    No Known Activations