© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40994
    Prev
    Next
    INDEX
    Explanations

    get/add/remove verb + noun

    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
    ↵↵
    -2.81
     ursprüng
    -2.30
     жена
    -2.27
     แต่
    -2.22
     französische
    -2.20
    -2.20
     mirando
    -2.17
    这意味着
    -2.03
     \
    -2.00
     tocando
    -1.97
    POSITIVE LOGITS
    OUTUBE
    2.64
    鵟
    2.50
     terlaris
    2.45
    鹀
    2.39
    Ꮔ
    2.34
    Various
    2.34
     mengucap
    2.33
    栊
    2.20
     menghubungi
    2.19
    2
    2.19
    Activations Density 0.001%

    No Known Activations