© 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. 22-GEMMASCOPE-RES-131K
    7. 72333
    Prev
    Next
    INDEX
    Explanations

    international words

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

    The neuron strongly responds to long, technical, domain‐specific nouns and jargon (e.g., specialized scientific terminology).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    🏡
    -1.05
    だから
    -1.02
    😀
    -1.00
    ❣
    -1.00
    😄
    -0.97
     Quindi
    -0.96
    😋
    -0.96
     Sì
    -0.95
     joan
    -0.95
     ！
    -0.94
    POSITIVE LOGITS
     acuer
    1.09
     apetito
    1.06
     découvrez
    1.05
     идеально
    1.01
     markiert
    0.98
     teratur
    0.97
    大満足
    0.96
     trazer
    0.96
    摇了
    0.95
    Zitat
    0.94
    Activations Density 0.585%

    No Known Activations