© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72571
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
     kolejne
    -1.46
     maceta
    -1.39
    Kapcsolódó
    -1.39
     они
    -1.38
     şek
    -1.37
    同上
    -1.37
    .}(
    -1.30
     вместо
    -1.30
     nowych
    -1.29
    ждением
    -1.28
    POSITIVE LOGITS
     vitrine
    1.49
     only
    1.44
     broderie
    1.40
     rapi
    1.33
    ！
    1.31
     NOU
    1.30
     lakini
    1.27
     balenciaga
    1.27
     exquis
    1.27
     chemise
    1.27
    Activations Density 0.047%

    No Known Activations