© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24900
    Prev
    Next
    INDEX
    Explanations

    possessive determiners in code

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     része
    -1.01
    ximately
    -0.96
    twas
    -0.95
    provides
    -0.93
     hosszú
    -0.93
    ティア
    -0.92
     llevará
    -0.92
     összefoglaló
    -0.92
    ﾟ
    -0.91
    穿搭
    -0.91
    POSITIVE LOGITS
     their
    1.59
     its
    0.99
     jú
    0.93
    Their
    0.90
     их
    0.90
     wrath
    0.88
     ihrer
    0.86
     dolorosa
    0.85
     ihren
    0.85
     їх
    0.85
    Activations Density 0.034%

    No Known Activations