© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

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

    The neuron is picking out quotation‐mark tokens surrounding quoted 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_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
    了一口
    -1.98
    🌟
    -1.94
    ꦮ
    -1.91
    If
    -1.82
    ization
    -1.80
    var
    -1.78
    ｇ
    -1.77
    zież
    -1.75
     Seil
    -1.75
     zei
    -1.74
    POSITIVE LOGITS
    <bos>
    2.48
     agarre
    2.11
     '
    2.08
     Länge
    2.00
    uterte
    1.91
    のいい
    1.89
     cœurs
    1.87
     Menschheit
    1.86
     événements
    1.84
     détails
    1.80
    Activations Density 0.002%

    No Known Activations