© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    punctuation then "Courtesy"

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

    The neuron sharply responds to sentence‐ending punctuation (especially “.”, “!”, and “?” at the ends of sentences).

    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
     It
    -2.47
     The
    -2.09
     However
    -1.96
     In
    -1.91
     that
    -1.84
     it
    -1.80
     On
    -1.65
     One
    -1.63
     Since
    -1.60
     in
    -1.55
    POSITIVE LOGITS
    ↵
    1.68
    Struktur
    1.52
     rafra
    1.52
     poft
    1.52
     entornos
    1.50
     rembour
    1.50
    
    1.48
     étan
    1.46
     ujedno
    1.45
     fuis
    1.45
    Activations Density 0.304%

    No Known Activations