© 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. 10-GEMMASCOPE-RES-131K
    7. 84012
    Prev
    Next
    INDEX
    Explanations

    nouns following prepositions or possessives

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。”
    -1.47
     —
    -1.34
    ”,
    -1.34
     you
    -1.30
    ↵
    -1.23
    ánky
    -1.23
     लड़
    -1.22
    、
    -1.20
    нути
    -1.19
    ”。
    -1.17
    POSITIVE LOGITS
     Should
    1.41
     Lengkap
    1.40
    Should
    1.38
     juiz
    1.30
     beijo
    1.28
     anúncio
    1.24
     skla
    1.24
     Whether
    1.24
     órg
    1.23
     that
    1.21
    Activations Density 0.133%

    No Known Activations