© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    orbit or orbital motion

    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
    馐
    -2.69
    袛
    -2.63
     necessárias
    -2.39
    糴
    -2.39
     circunstancia
    -2.39
    艄
    -2.28
     they
    -2.25
    靫
    -2.25
    ñador
    -2.23
     ſont
    -2.23
    POSITIVE LOGITS
    ↵↵
    3.28
    n
    2.73
    🢒
    2.42
     ira
    2.41
    to
    2.41
    t
    2.39
    料
    2.36
    2.33
    寕
    2.27
    ligibility
    2.22
    Activations Density 0.003%

    No Known Activations