© 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. 11559
    Prev
    Next
    INDEX
    Explanations

    highlighting or highlighted text

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

    The neuron activates whenever the token “highlight” appears.

    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
     to
    -2.33
    ↵↵
    -1.84
    endian
    -1.73
     But
    -1.70
     ก็
    -1.68
     It
    -1.64
    </i>
    -1.60
    ⩩
    -1.58
     about
    -1.58
    ES
    -1.56
    POSITIVE LOGITS
     měla
    1.81
     zůst
    1.75
     měli
    1.74
    有著
    1.70
    是個
    1.70
     nyní
    1.67
    一開始
    1.67
    苼
    1.66
     někdo
    1.66
     \"
    1.64
    Activations Density 0.014%

    No Known Activations