© 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. 22810
    Prev
    Next
    INDEX
    Explanations

    expresses gladness

    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
     a
    -1.98
     on
    -1.84
     Also
    -1.66
    Bahkan
    -1.63
    Sebelumnya
    -1.56
     also
    -1.55
     tránsito
    -1.55
    散文
    -1.55
    ....
    -1.53
    .....
    -1.53
    POSITIVE LOGITS
     they
    1.95
    ՚
    1.84
     primeira
    1.73
     Nasi
    1.55
     primeiros
    1.54
    泚
    1.48
    犼
    1.48
     resul
    1.45
    橚
    1.45
    艄
    1.44
    Activations Density 0.014%

    No Known Activations