© 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. 119797
    Prev
    Next
    INDEX
    Explanations

    navigation and author links

    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
    たび
    -1.88
     our
    -1.84
    そういえば
    -1.73
    لينا
    -1.71
    余談
    -1.71
     hjemmeside
    -1.70
     черные
    -1.70
     ($('#
    -1.68
    说说
    -1.68
    Ᏻ
    -1.66
    POSITIVE LOGITS
    5
    2.67
    8
    2.66
    9
    2.61
    3
    2.61
    0
    2.52
    7
    2.39
     '
    2.30
    4
    2.28
    1
    2.25
    2
    2.22
    Activations Density 0.202%

    No Known Activations