© 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. 34-GEMMASCOPE-RES-131K
    7. 91660
    Prev
    Next
    INDEX
    Explanations

    api and apis

    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_34/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
     Zusammenfassung
    -0.69
    ܪ
    -0.68
     listening
    -0.67
     доби
    -0.66
     прилага
    -0.65
     Murphy
    -0.65
     Resume
    -0.64
    сел
    -0.63
     Marlin
    -0.63
     специаль
    -0.63
    POSITIVE LOGITS
    ______________
    0.80
    Mitte
    0.77
     crede
    0.75
    洢
    0.75
    genomen
    0.75
    صه
    0.75
     elegancia
    0.75
    転
    0.75
    enedor
    0.75
     copied
    0.75
    Activations Density 0.038%

    No Known Activations