© 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. 123879
    Prev
    Next
    INDEX
    Explanations

    action verbs with objects

    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
     cómoda
    -1.47
     comodidad
    -1.45
     bricolaje
    -1.45
     krijg
    -1.41
    鋮
    -1.40
     helicópter
    -1.35
     artesanía
    -1.35
    之类的
    -1.34
     atractiva
    -1.34
     senderismo
    -1.34
    POSITIVE LOGITS
    it
    1.70
     of
    1.58
    if
    1.52
    臵
    1.41
    琑
    1.41
    om
    1.35
    ges
    1.32
    U
    1.32
    S
    1.28
    ності
    1.25
    Activations Density 0.015%

    No Known Activations