© 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. 111429
    Prev
    Next
    INDEX
    Explanations

    foreign, alien, stranger, odd

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

    The neuron activates on words conveying “foreignness” or “outsider‐ness” (e.g. stranger, alien, xenobiotic, estrangeira).

    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
    ть
    -1.77
    る
    -1.77
     enam
    -1.67
     aint
    -1.66
     Национа
    -1.62
    ريكية
    -1.61
    なのは
    -1.60
     fantástica
    -1.56
     espiritual
    -1.55
    щении
    -1.52
    POSITIVE LOGITS
    }
    2.39
    but
    1.99
    even
    1.93
    ⸎
    1.88
    禵
    1.77
    ᠂
    1.77
    を中心
    1.75
     contextes
    1.74
     iſt
    1.72
     लेकिन
    1.72
    Activations Density 0.018%

    No Known Activations