© 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. 25104
    Prev
    Next
    INDEX
    Explanations

    magnitude, proportion, and comparison

    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
     which
    -1.02
    ględ
    -1.01
    :),
    -0.95
    Kesimpulan
    -0.94
     and
    -0.94
    Masukkan
    -0.94
     potentially
    -0.94
     should
    -0.94
     explicitly
    -0.93
     wichtigsten
    -0.93
    POSITIVE LOGITS
     pasaron
    1.23
     pudieron
    1.22
    odora
    1.11
    tauchen
    1.09
     lesz
    1.09
     llenos
    1.08
     encontraron
    1.06
    raa
    1.05
     continúan
    1.05
     tuvieron
    1.04
    Activations Density 0.108%

    No Known Activations