© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52741
    Prev
    Next
    INDEX
    Explanations

    possessives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     внутренних
    0.46
     internalization
    0.42
    ण्याची
    0.41
    ᱹ
    0.41
    ันทร์
    0.40
    மீ
    0.40
     physicality
    0.40
     namesake
    0.39
    ันท
    0.39
     ownership
    0.39
    POSITIVE LOGITS
     ആണ്
    0.51
    o
    0.49
    ap
    0.48
    et
    0.47
    do
    0.47
    ia
    0.44
     是
    0.44
    ane
    0.44
    ateau
    0.44
     لا
    0.44
    Activations Density 0.030%

    No Known Activations