© 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. 60789
    Prev
    Next
    INDEX
    Explanations

    Jaime, Miguel, Webb, Merritt

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

    The neuron activates on individual capitalized personal names (i.e. tokens that are people’s given names or surnames).

    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
    0
    -3.56
    嗵
    -3.09
    หรือ
    -2.92
     magasiner
    -2.67
    〬
    -2.59
    躂
    -2.56
    IANGLES
    -2.47
     или
    -2.45
     atau
    -2.42
    猹
    -2.42
    POSITIVE LOGITS
    …
    2.59
    轳
    2.48
    {
    2.38
    The
    2.36
    过了
    2.20
    $
    2.19
    ?
    2.16
     possam
    2.14
    .​
    2.14
    ).
    2.14
    Activations Density 0.039%

    No Known Activations