© 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. 106263
    Prev
    Next
    INDEX
    Explanations

    past simple verbs following nouns

    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
    Materiaal
    -2.16
    Kleur
    -1.91
    Welke
    -1.84
    Prijs
    -1.80
    Vraag
    -1.77
    Waarom
    -1.74
    Gebruik
    -1.65
    Veel
    -1.61
    Conclusie
    -1.52
     kantoor
    -1.50
    POSITIVE LOGITS
     outspoken
    1.63
     overruled
    1.56
     therewith
    1.56
    Nr
    1.49
    etera
    1.40
     Especially
    1.38
     nr
    1.37
    Geplaatst
    1.33
    cfr
    1.30
     halve
    1.27
    Activations Density 0.900%

    No Known Activations