© 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. 59821
    Prev
    Next
    INDEX
    Explanations

    states and concepts

    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
    groet
    -1.48
     in
    -1.45
     atau
    -1.42
    ˶
    -1.39
     mijn
    -1.39
    及び
    -1.33
    kenal
    -1.30
    libatkan
    -1.30
     during
    -1.30
    borsa
    -1.30
    POSITIVE LOGITS
     zood
    1.51
     interieur
    1.50
     olie
    1.48
     oogen
    1.48
     barnet
    1.47
    gencias
    1.45
     enz
    1.45
    が違う
    1.44
     volk
    1.41
     spoor
    1.41
    Activations Density 0.131%

    No Known Activations