© 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. 101088
    Prev
    Next
    INDEX
    Explanations

    first name followed by surname

    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
     vivido
    -1.57
     asust
    -1.52
    媖
    -1.46
    ꪔ
    -1.42
     fantastique
    -1.38
     señalado
    -1.35
     grec
    -1.34
    帏
    -1.34
    ﹶ
    -1.34
     sufrido
    -1.34
    POSITIVE LOGITS
     they
    1.74
     that
    1.71
     their
    1.63
     there
    1.51
     medži
    1.42
     valsty
    1.41
     gyvento
    1.37
     vandens
    1.34
     of
    1.34
     this
    1.30
    Activations Density 0.078%

    No Known Activations