© 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. 34-GEMMASCOPE-RES-131K
    7. 102552
    Prev
    Next
    INDEX
    Explanations

    possessive phrases with 'their'

    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_34/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
    pixabay
    -0.83
     عملیات
    -0.82
    bedien
    -0.80
     utilisons
    -0.79
    χή
    -0.77
    里有
    -0.75
    ).”
    -0.75
    ը
    -0.74
     insanlar
    -0.74
     dangereux
    -0.73
    POSITIVE LOGITS
     peoples
    3.08
     childrens
    2.23
    用户的
    1.80
    者の
    1.69
    者的
    1.65
    さんの
    1.56
     womens
    1.55
    人的
    1.54
    들의
    1.54
    childrens
    1.53
    Activations Density 0.206%

    No Known Activations