© 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. 41095
    Prev
    Next
    INDEX
    Explanations

    Java, Servlets, Beans, Applets

    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
    .
    -1.44
     fraî
    -1.31
     enceinte
    -1.30
    lendir
    -1.30
    的作品
    -1.29
     loue
    -1.28
     "..\..\..\
    -1.26
     ENGINEERS
    -1.25
     kazi
    -1.24
    ﾞ
    -1.24
    POSITIVE LOGITS
     to
    1.87
     that
    1.59
    itzar
    1.48
     Ellos
    1.45
     wła
    1.39
     or
    1.38
     Selecciona
    1.38
     Obtén
    1.37
    ↵↵↵↵↵↵↵↵↵
    1.35
     Generales
    1.35
    Activations Density 0.240%

    No Known Activations