© 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. 75552
    Prev
    Next
    INDEX
    Explanations

    Chinese, Spanish, Arabic, Korean, and English terms

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find ellipsis punctuation (series of consecutive periods).

    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
     Both
    -2.67
    两人的
    -2.61
    </u>
    -2.45
    攻擊
    -2.36
     Only
    -2.30
    If
    -2.30
    Currently
    -2.28
    〰
    -2.28
    ☀
    -2.23
    Only
    -2.22
    POSITIVE LOGITS
    艄
    2.95
    臯
    2.94
    {
    2.63
    gencias
    2.58
     که
    2.53
    푙
    2.50
     unable
    2.48
    "'
    2.47
    that
    2.47
    万物
    2.44
    Activations Density 0.026%

    No Known Activations