© 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. 83702
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by actions or states

    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
    Negative Logits
     from
    -1.55
    ladesh
    -1.47
     استیل
    -1.41
    cerpts
    -1.35
    iliki
    -1.34
     them
    -1.34
     частей
    -1.34
     setDescription
    -1.30
     setImage
    -1.30
     They
    -1.30
    POSITIVE LOGITS
     
    1.46
    彼女は
    1.45
    邻居
    1.45
    ebabkan
    1.28
    BeforeMethod
    1.24
    erapa
    1.22
     rapides
    1.20
     élevée
    1.20
    ífer
    1.20
    今度は
    1.19
    Activations Density 0.231%

    No Known Activations