© 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. 40529
    Prev
    Next
    INDEX
    Explanations

    Thor, Iida, Blair, Leia

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

    The neuron fires on capitalized proper names—especially fictional character and place names.

    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
     itself
    -1.21
    良かったです
    -1.21
     ($('#
    -1.18
    imetsu
    -1.13
    すでに
    -1.12
    胪
    -1.12
    鹇
    -1.12
    よくある
    -1.09
    孭
    -1.09
    ötz
    -1.09
    POSITIVE LOGITS
     closely
    1.22
     има
    1.21
    」、「
    1.14
    ↵↵
    1.12
    <tr>
    1.09
     columna
    1.09
     determinado
    1.09
     complément
    1.08
    顿时
    1.07
     cuire
    1.02
    Activations Density 0.011%

    No Known Activations