© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62222
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite

    multiple, compulsion, compress, where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Ռ
    0.50
    ﺗ
    0.49
    ინ
    0.47
    dı
    0.46
    ല
    0.46
    Perfil
    0.44
    ИН
    0.44
    ﴿
    0.43
    쉬
    0.43
    𝓜
    0.43
    POSITIVE LOGITS
     summons
    0.46
     journalist
    0.46
     gavel
    0.45
     newspaper
    0.45
     loan
    0.44
     kiln
    0.44
     acudir
    0.43
     bicycle
    0.43
     Newspaper
    0.43
     dispatcher
    0.43
    Activations Density 0.000%

    No Known Activations