© 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. 99665
    Prev
    Next
    INDEX
    Explanations

    no"?>

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

    This neuron fires on the literal attribute value “no” in XML/HTML declarations (e.g. standalone="no" or content="no").

    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
    viembre
    -3.44
    leggio
    -3.03
    us
    -2.42
    <bos>
    -2.41
     榜
    -2.38
    埈
    -2.36
     药
    -2.36
    踽
    -2.34
     市场
    -2.31
    勠
    -2.30
    POSITIVE LOGITS
    1
    2.81
    9
    2.66
    随即
    2.45
    を選ぶ
    2.38
     با
    2.38
    2
    2.36
    ครื่อง
    2.33
     một
    2.30
     
    2.28
    8
    2.28
    Activations Density 0.005%

    No Known Activations