© 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. 22-GEMMASCOPE-RES-131K
    7. 32635
    Prev
    Next
    INDEX
    Explanations

    gerunds or nouns followed by "of"

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     बाद
    -1.05
    見えます
    -1.04
     versuchen
    -1.02
     If
    -0.98
     兩
    -0.97
     alimentare
    -0.97
     aisladas
    -0.95
    If
    -0.95
     to
    -0.94
    Often
    -0.94
    POSITIVE LOGITS
     of
    1.36
     among
    1.27
    itisation
    1.13
    雠
    1.12
    itization
    1.11
     mété
    1.07
    among
    1.05
    了我
    1.05
     gada
    1.05
    akses
    1.03
    Activations Density 0.125%

    No Known Activations