© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29106
    Prev
    Next
    INDEX
    Explanations

    different ways or versions

    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
    ienė
    -1.28
    亿美元
    -1.27
    reqs
    -1.20
     triko
    -1.19
     ملابس
    -1.16
     także
    -1.16
     również
    -1.16
    φορά
    -1.14
    了好
    -1.14
     firs
    -1.14
    POSITIVE LOGITS
     have
    1.65
     unterschied
    1.32
     believe
    1.30
     keep
    1.27
     get
    1.23
     разные
    1.23
     approaches
    1.15
     diferentes
    1.13
     uses
    1.12
     differing
    1.11
    Activations Density 0.230%

    No Known Activations