© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106699
    Prev
    Next
    INDEX
    Explanations

    associated Press, foreign words, slug, URLs

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

    The neuron flags non‐prose tokens—such as metadata markers, code/XML/PHP snippets, foreign‐language words, and numeric or URL fragments—rather than ordinary English running 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_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
    不敢
    -1.14
    是一个
    -1.01
     a
    -0.94
    不太
    -0.91
    是个
    -0.91
    不可能
    -0.90
    不會
    -0.90
    不再
    -0.89
    可以
    -0.87
    不需要
    -0.84
    POSITIVE LOGITS
     môžu
    0.99
     môže
    0.92
     összefoglaló
    0.88
     regalías
    0.85
     lapses
    0.83
     excelled
    0.82
    のようです
    0.82
     renovables
    0.82
     soutě
    0.82
    已经在
    0.82
    Activations Density 0.022%

    No Known Activations