© 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. 34-GEMMASCOPE-RES-131K
    7. 6908
    Prev
    Next
    INDEX
    Explanations

    can be chosen

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

    This neuron activates on Chinese modal words indicating ability or possibility (e.g., “可,” “能,” “自由”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    セラー
    -0.93
    ArgsConstructor
    -0.93
     dolayı
    -0.90
    Claro
    -0.87
    pires
    -0.86
    そして
    -0.82
    𝔗
    -0.82
    奶油
    -0.79
    ra
    -0.79
    などを
    -0.78
    POSITIVE LOGITS
    為に
    1.08
    の一覧
    1.01
     всички
    0.85
    是一個
    0.85
    づけ
    0.84
     hacia
    0.84
    ようになりました
    0.83
     getById
    0.82
    During
    0.82
    ból
    0.82
    Activations Density 0.011%

    No Known Activations