© 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. 94204
    Prev
    Next
    INDEX
    Explanations

    past auxiliary verbs

    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
    Had
    -1.31
     Had
    -1.09
     be
    -1.09
    出来ない
    -1.05
    缁
    -1.02
    Saw
    -0.93
     being
    -0.90
    情報の
    -0.85
    ANI
    -0.84
    できない
    -0.84
    POSITIVE LOGITS
     telah
    1.09
     have
    1.05
     đã
    1.02
     olmuş
    0.81
     έχουν
    0.79
    lamda
    0.79
     incred
    0.79
     linden
    0.78
     has
    0.77
    culada
    0.76
    Activations Density 0.011%

    No Known Activations