© 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. 100051
    Prev
    Next
    INDEX
    Explanations

    more + descriptor

    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
     of
    -3.11
    fillment
    -2.20
     momentan
    -1.94
    for
    -1.77
     that
    -1.76
    on
    -1.72
     ส์
    -1.67
    籏
    -1.63
    cels
    -1.63
     technisch
    -1.63
    POSITIVE LOGITS
     dispuesto
    1.81
     preparado
    1.72
     oculto
    1.70
     preocupado
    1.69
     manchas
    1.69
     entregado
    1.67
    最初に
    1.62
     prevalent
    1.61
     EVERY
    1.59
     atendido
    1.59
    Activations Density 0.073%

    No Known Activations