© 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. 16598
    Prev
    Next
    INDEX
    Explanations

    Sub-Saharan Africa countries

    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
     methods
    -0.98
     органі
    -0.94
    After
    -0.94
     profoundly
    -0.94
     vitally
    -0.93
     exquisitely
    -0.92
     Reiz
    -0.90
    نجليز
    -0.89
     pemerintah
    -0.89
    Before
    -0.88
    POSITIVE LOGITS
    ws
    1.00
    などが
    0.94
    avra
    0.90
    usually
    0.87
    wie
    0.84
    vo
    0.82
    ract
    0.82
    jing
    0.81
    cj
    0.80
    rp
    0.79
    Activations Density 0.017%

    No Known Activations