© 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. 124133
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions

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

    The neuron strongly activates on commas (the comma punctuation character).

    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
     '';
    -2.14
     ؟
    -2.05
    5
    -1.96
     Espagne
    -1.84
    The
    -1.77
     rumahnya
    -1.73
     mystère
    -1.71
    9
    -1.70
     zoude
    -1.68
    leine
    -1.66
    POSITIVE LOGITS
     jsou
    1.91
    躄
    1.90
    闔
    1.83
    NegativeButton
    1.82
    だけではなく
    1.81
    が必要です
    1.80
     decipher
    1.79
    だけでなく
    1.79
    yelitis
    1.78
    ocios
    1.70
    Activations Density 0.059%

    No Known Activations