© 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. 10-GEMMASCOPE-RES-131K
    7. 71658
    Prev
    Next
    INDEX
    Explanations

    holidays and events

    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
    핌
    -1.27
    人生
    -1.23
     from
    -1.22
    ,​
    -1.19
     end
    -1.16
    didn
    -1.10
     opzioni
    -1.09
    }^{+\
    -1.08
    intérieur
    -1.08
     }}$
    -1.08
    POSITIVE LOGITS
     بازار
    1.30
     моих
    1.20
    processor
    1.15
     bús
    1.13
    紆
    1.13
    lève
    1.13
    дизайн
    1.12
     asiática
    1.09
    presenta
    1.09
     eri
    1.09
    Activations Density 0.145%

    No Known Activations