© 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. 100588
    Prev
    Next
    INDEX
    Explanations

    installed in or at

    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
     it
    -1.49
     peruana
    -1.44
     sekitarnya
    -1.34
     необхідно
    -1.32
     two
    -1.30
    頻繁
    -1.30
    q
    -1.29
     three
    -1.28
     its
    -1.25
     nahezu
    -1.24
    POSITIVE LOGITS
    ⢅
    1.43
     to
    1.42
     pracu
    1.40
     stali
    1.38
     další
    1.35
     livros
    1.34
    ҿ
    1.31
    ICIÓN
    1.30
     angiel
    1.30
     Jahren
    1.27
    Activations Density 0.110%

    No Known Activations