© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110485
    Prev
    Next
    INDEX
    Explanations

    notable or elusive entities

    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
    szám
    -1.55
    Hilsen
    -1.45
    Carex
    -1.34
    不仅仅
    -1.32
    ﺕ
    -1.26
    .«
    -1.22
    逋
    -1.16
    槼
    -1.15
     számára
    -1.15
    lightly
    -1.15
    POSITIVE LOGITS
     you
    1.39
     time
    1.36
     question
    1.32
     dreaded
    1.31
    after
    1.30
     cuya
    1.29
    less
    1.27
     we
    1.27
    ŚĆ
    1.25
    )):
    
    1.24
    Activations Density 0.057%

    No Known Activations