© 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. 34-GEMMASCOPE-RES-131K
    7. 47141
    Prev
    Next
    INDEX
    Explanations

    modal verbs like "should" or "ought"

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﾋ
    -0.76
     Vort
    -0.75
    iliano
    -0.73
    Kurz
    -0.68
     запро
    -0.68
    渤
    -0.68
    קת
    -0.68
    Ikke
    -0.67
    Når
    -0.65
    kuuta
    -0.65
    POSITIVE LOGITS
    should
    2.44
     should
    2.34
     SHOULD
    2.23
    Should
    2.22
    ould
    2.22
     Should
    2.08
    hould
    1.86
    应该
    1.66
     ought
    1.56
     должно
    1.55
    Activations Density 0.026%

    No Known Activations