© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85722
    Prev
    Next
    INDEX
    Explanations

    Vince and Webb

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

    The neuron fires on proper personal names mentioned in the 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
    .’
    -2.89
    ↵↵
    -2.59
    ).
    -2.47
    !”
    -2.45
    就像是
    -2.44
    ᅫ
    -2.38
    ,”
    -2.38
    .”
    -2.34
     человек
    -2.34
    姈
    -2.31
    POSITIVE LOGITS
    嵙
    2.77
    立场
    2.58
    sandalia
    2.56
    感じ
    2.56
    話が
    2.55
    感じた
    2.47
     hó
    2.38
    釭
    2.33
    鹮
    2.33
    小孩子
    2.33
    Activations Density 0.007%

    No Known Activations