© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71579
    Prev
    Next
    INDEX
    Explanations

    French or Dutch words

    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
    Can
    -1.52
    他說
    -1.51
    Is
    -1.48
     näch
    -1.38
    他和
    -1.37
     gewal
    -1.36
    ↵↵
    -1.34
     beantragt
    -1.31
     некоторые
    -1.30
     first
    -1.30
    POSITIVE LOGITS
    ementara
    1.85
     pittores
    1.81
     berge
    1.72
     剧照
    1.64
     verbe
    1.64
     vanille
    1.63
     brune
    1.62
    formatie
    1.60
     jardins
    1.60
     juſ
    1.57
    Activations Density 0.002%

    No Known Activations