© 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. 22-GEMMASCOPE-RES-131K
    7. 39991
    Prev
    Next
    INDEX
    Explanations

    punctuation and which

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

    The neuron is a punctuation detector that particularly lights up on commas (and similar clause-separating punctuation).

    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
     lakini
    -1.08
     allah
    -1.05
     presunto
    -0.98
     épices
    -0.97
     satisfacer
    -0.97
     แต่
    -0.96
     プル
    -0.96
     وہ
    -0.94
    geordnete
    -0.94
    顳
    -0.94
    POSITIVE LOGITS
     to
    1.22
     so
    1.14
     There
    1.09
     which
    1.05
     afin
    1.02
     If
    0.97
    (),
    0.97
     wegen
    0.94
     “
    0.94
     (
    0.91
    Activations Density 0.045%

    No Known Activations