© 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. 64302
    Prev
    Next
    INDEX
    Explanations

    overall quantity or ratio

    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
     on
    -1.03
    Metal
    -0.91
     GlobalKey
    -0.89
    Humans
    -0.89
     for
    -0.88
    馭
    -0.88
     Metal
    -0.85
     inconsciente
    -0.85
    ilización
    -0.84
    一些
    -0.83
    POSITIVE LOGITS
     total
    1.35
     전체
    1.24
     entire
    1.20
     overall
    1.15
     énorm
    1.02
    總
    0.98
    一个月
    0.98
     durer
    0.96
    wnia
    0.96
    ENSIVE
    0.96
    Activations Density 0.013%

    No Known Activations