© 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. 10-GEMMASCOPE-RES-131K
    7. 68942
    Prev
    Next
    INDEX
    Explanations

    ending s) notation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     parís
    -2.19
     authenti
    -1.95
     RSITY
    -1.90
     mikina
    -1.89
    达到了
    -1.88
     Lettres
    -1.88
     armani
    -1.87
     AMOR
    -1.84
     mahdol
    -1.83
    They
    -1.79
    POSITIVE LOGITS
     to
    3.77
    轳
    2.22
    s
    2.11
    },
    2.03
    在我
    2.00
    ?”
    1.93
     nel
    1.91
    ască
    1.87
    ৢ
    1.87
     太郎
    1.86
    Activations Density 0.022%

    No Known Activations