© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     said
    0.97
     says
    0.96
     mengatakan
    0.94
    said
    0.91
    says
    0.87
     বলেছেন
    0.87
     يقول
    0.87
    说
    0.82
     zeggen
    0.81
     saying
    0.80
    POSITIVE LOGITS
     added
    3.06
     Added
    2.95
    Added
    2.95
    added
    2.88
     adds
    2.73
     adding
    2.72
     доба
    2.70
     добавля
    2.70
    添加
    2.56
     ajouté
    2.53
    Activations Density 0.117%

    No Known Activations