© 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. 6766
    Prev
    Next
    INDEX
    Explanations

    "which" then it or they

    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
     llorando
    -1.56
     också
    -1.53
     tambien
    -1.43
     sosteniendo
    -1.41
     sonriendo
    -1.40
    聍
    -1.40
    ܇
    -1.38
    ┥
    -1.38
     Something
    -1.35
     caminando
    -1.35
    POSITIVE LOGITS
     this
    1.95
     where
    1.52
     it
    1.48
     usadas
    1.41
    (
    1.30
    č
    1.30
     específica
    1.20
    versible
    1.16
    ész
    1.16
    问题
    1.14
    Activations Density 0.066%

    No Known Activations