© 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. 86076
    Prev
    Next
    INDEX
    Explanations

    Kä + ler/ren

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

    The neuron responds almost exclusively to the token “was.”

    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
    ႐
    -2.45
    9
    -2.38
     jedem
    -2.38
     selben
    -2.34
    6
    -2.33
    。“
    -2.23
     ежедневно
    -2.23
    il
    -2.23
    ikusbot
    -2.22
     שלהם
    -2.19
    POSITIVE LOGITS
    \
    2.27
    恹
    2.19
     Its
    2.03
     ツリー
    2.00
     $^{
    1.97
     you
    1.95
    はじめ
    1.91
    '];
    1.91
     Yesterday
    1.91
    ました
    1.90
    Activations Density 0.000%

    No Known Activations