© 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. 127208
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
     aplicable
    -1.52
     incluyendo
    -1.43
    ＆
    -1.41
    𐄁
    -1.39
    ys
    -1.38
    MAXN
    -1.38
    ísimas
    -1.36
    合わせた
    -1.35
    aking
    -1.34
     imposible
    -1.34
    POSITIVE LOGITS
     its
    2.03
     what
    1.86
     all
    1.74
     more
    1.63
     our
    1.63
     how
    1.61
     it
    1.57
     a
    1.55
     your
    1.51
     we
    1.50
    Activations Density 0.177%

    No Known Activations