© 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. 70206
    Prev
    Next
    INDEX
    Explanations

    possessive people/someone

    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
     are
    -2.22
     jedynie
    -1.62
     that
    -1.60
     significantly
    -1.45
     of
    -1.44
     such
    -1.38
    Curtir
    -1.34
     like
    -1.34
     unlike
    -1.33
    ואה
    -1.33
    POSITIVE LOGITS
     mengungkapkan
    1.89
     menilai
    1.55
     kaplama
    1.43
     menceritakan
    1.42
     menegaskan
    1.41
     داشتند
    1.37
     выборе
    1.37
     melindungi
    1.36
     Frankrijk
    1.36
     нашем
    1.35
    Activations Density 0.042%

    No Known Activations