© 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. 58016
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     feminina
    -1.34
     hadas
    -1.30
     folo
    -1.28
     puisqu
    -1.27
    之后
    -1.23
    jamientos
    -1.20
    켓
    -1.20
    뻗
    -1.19
     pascua
    -1.19
    ység
    -1.18
    POSITIVE LOGITS
     simplemente
    1.68
     estrictamente
    1.39
    原來
    1.38
     their
    1.27
     particularmente
    1.24
     econó
    1.23
     pelear
    1.20
    를
    1.20
     were
    1.20
     you
    1.20
    Activations Density 0.058%

    No Known Activations