© 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. 29044
    Prev
    Next
    INDEX
    Explanations

    think or talking introducing examples

    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
     would
    -1.36
    couvrez
    -1.30
     it
    -1.29
     pessoais
    -1.27
     besteht
    -1.25
     endroits
    -1.25
     パリ
    -1.23
    Alguns
    -1.23
     funcione
    -1.22
    cursions
    -1.20
    POSITIVE LOGITS
     triko
    1.32
     mémor
    1.30
    ULTURAL
    1.28
     doba
    1.27
     teratur
    1.25
    ྃ
    1.25
     wiederhol
    1.23
     også
    1.23
    𝚃
    1.23
    と思いました
    1.23
    Activations Density 0.015%

    No Known Activations