© 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. 24901
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
     нарушение
    -0.94
    thold
    -0.94
    édez
    -0.90
    ódio
    -0.89
    最も
    -0.85
    իա
    -0.85
     lintas
    -0.84
    chafter
    -0.82
    わけではない
    -0.82
    ylate
    -0.81
    POSITIVE LOGITS
     defaulted
    0.82
    ">(
    0.80
    вут
    0.77
    の存在
    0.77
    mo
    0.77
     kk
    0.76
    lovely
    0.76
    az
    0.75
     আর
    0.75
    beg
    0.74
    Activations Density 0.076%

    No Known Activations