© 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. 15781
    Prev
    Next
    INDEX
    Explanations

    specific terms and names

    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
     is
    -1.73
     on
    -1.54
    —
    -1.34
    ),
    -1.25
     nawet
    -1.23
     señalar
    -1.23
    ).
    -1.19
     J
    -1.15
    ?
    -1.14
    ,”
    -1.13
    POSITIVE LOGITS
     gonzález
    1.33
     gonz
    1.25
     cilvē
    1.24
    ⽀
    1.21
     lópez
    1.21
    Angebot
    1.20
     garcía
    1.20
     biraz
    1.19
    Largeur
    1.18
     goku
    1.16
    Activations Density 0.413%

    No Known Activations