© 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. 20995
    Prev
    Next
    INDEX
    Explanations

    popular with or among

    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
     a
    -2.25
     one
    -1.50
    されてる
    -1.42
     acogedor
    -1.39
     that
    -1.34
    新しく
    -1.34
     what
    -1.31
    这是一
    -1.31
     there
    -1.30
    mintaan
    -1.30
    POSITIVE LOGITS
    >"+
    1.60
    ทย
    1.60
    utiva
    1.59
    
    1.58
     både
    1.55
     dades
    1.54
     فترة
    1.52
    égek
    1.52
    gulls
    1.51
    склад
    1.49
    Activations Density 0.023%

    No Known Activations